From 9530d3a6d8ad24d68bf35fcf396a8c9edeeb6df3 Mon Sep 17 00:00:00 2001
From: oobabooga <oobabooga4@gmail.com>
Date: Sun, 21 Dec 2025 15:30:54 -0300
Subject: [PATCH 01/11] UI: Improve hr (horizontal separator) style

---
 css/html_instruct_style.css | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/css/html_instruct_style.css b/css/html_instruct_style.css
index 6dee0a89..5a0338a5 100644
--- a/css/html_instruct_style.css
+++ b/css/html_instruct_style.css
@@ -27,6 +27,10 @@
     border-color: #ffffff75 !important;
 }
 
+.dark .prose hr {
+    border-color: #ffffff75 !important;
+}
+
 .chat .message-body :is(p, ul, ol) {
     margin: 1.25em 0 !important;
 }

From 1066fe8c2110a8a366c7bdf945f0489bd8d1b113 Mon Sep 17 00:00:00 2001
From: oobabooga <oobabooga4@gmail.com>
Date: Sun, 21 Dec 2025 15:32:02 -0300
Subject: [PATCH 02/11] UI: Improve table styles (more minimalistic)

---
 css/main.css | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/css/main.css b/css/main.css
index e7586960..376cfa6d 100644
--- a/css/main.css
+++ b/css/main.css
@@ -1797,3 +1797,20 @@ button#swap-height-width {
     top: 0;
     left: calc(100% - 174px);
 }
+
+table {
+  border-collapse: collapse;
+}
+
+table, tr, td, th, thead {
+  border: 0;
+}
+
+td + td,
+th + th { border-left: 1px solid; }
+
+tr + tr td,
+tr + tr th { border-top: 1px solid; }
+
+thead + tbody tr:first-child td,
+thead + tbody tr:first-child th { border-top: 1px solid; }

From a2ed640aa6271251520acbe4831fd860f5f44f1c Mon Sep 17 00:00:00 2001
From: oobabooga <oobabooga4@gmail.com>
Date: Sun, 21 Dec 2025 15:38:48 -0300
Subject: [PATCH 03/11] UI: Improved border color for tables + hr

---
 css/html_instruct_style.css | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/css/html_instruct_style.css b/css/html_instruct_style.css
index 5a0338a5..a7532cf6 100644
--- a/css/html_instruct_style.css
+++ b/css/html_instruct_style.css
@@ -19,16 +19,14 @@
     color: #d1d5db !important;
 }
 
-.chat .message-body :is(th, td) {
+.chat .message-body :is(th, td),
+.prose hr {
     border-color: #40404096 !important;
 }
 
-.dark .chat .message-body :is(th, td) {
-    border-color: #ffffff75 !important;
-}
-
+.dark .chat .message-body :is(th, td),
 .dark .prose hr {
-    border-color: #ffffff75 !important;
+    border-color: rgba(255, 255, 255, 0.3) !important;
 }
 
 .chat .message-body :is(p, ul, ol) {

From 6e2c4e9c23fbeb71fbbf4b97be6968351cd9ab7d Mon Sep 17 00:00:00 2001
From: Sergey 'Jin' Bostandzhyan <jin@mediatomb.cc>
Date: Tue, 6 Jan 2026 15:31:10 +0100
Subject: [PATCH 04/11] Fix loading models which have their eos token disabled
 (#7363)

---
 modules/models_settings.py | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/modules/models_settings.py b/modules/models_settings.py
index e9f19a06..15ff2830 100644
--- a/modules/models_settings.py
+++ b/modules/models_settings.py
@@ -83,7 +83,11 @@ def get_model_metadata(model):
 
         if 'tokenizer.chat_template' in metadata:
             template = metadata['tokenizer.chat_template']
-            eos_token = metadata['tokenizer.ggml.tokens'][metadata['tokenizer.ggml.eos_token_id']]
+            if 'tokenizer.ggml.eos_token_id' in metadata:
+                eos_token = metadata['tokenizer.ggml.tokens'][metadata['tokenizer.ggml.eos_token_id']]
+            else:
+                eos_token = ""
+
             if 'tokenizer.ggml.bos_token_id' in metadata:
                 bos_token = metadata['tokenizer.ggml.tokens'][metadata['tokenizer.ggml.bos_token_id']]
             else:

From bb3b7bc1979b90f3de2a5b8968c816adf7458856 Mon Sep 17 00:00:00 2001
From: oobabooga <112222186+oobabooga@users.noreply.github.com>
Date: Tue, 6 Jan 2026 10:23:58 -0800
Subject: [PATCH 05/11] Update llama.cpp

---
 requirements/full/requirements.txt                     | 4 ++--
 requirements/full/requirements_amd.txt                 | 4 ++--
 requirements/full/requirements_amd_noavx2.txt          | 4 ++--
 requirements/full/requirements_apple_intel.txt         | 4 ++--
 requirements/full/requirements_apple_silicon.txt       | 4 ++--
 requirements/full/requirements_cpu_only.txt            | 4 ++--
 requirements/full/requirements_cpu_only_noavx2.txt     | 4 ++--
 requirements/full/requirements_noavx2.txt              | 4 ++--
 requirements/portable/requirements.txt                 | 4 ++--
 requirements/portable/requirements_amd.txt             | 4 ++--
 requirements/portable/requirements_amd_noavx2.txt      | 4 ++--
 requirements/portable/requirements_apple_intel.txt     | 4 ++--
 requirements/portable/requirements_apple_silicon.txt   | 4 ++--
 requirements/portable/requirements_cpu_only.txt        | 4 ++--
 requirements/portable/requirements_cpu_only_noavx2.txt | 4 ++--
 requirements/portable/requirements_noavx2.txt          | 4 ++--
 requirements/portable/requirements_vulkan.txt          | 4 ++--
 requirements/portable/requirements_vulkan_noavx2.txt   | 4 ++--
 18 files changed, 36 insertions(+), 36 deletions(-)

diff --git a/requirements/full/requirements.txt b/requirements/full/requirements.txt
index 79292a9f..a7d3403f 100644
--- a/requirements/full/requirements.txt
+++ b/requirements/full/requirements.txt
@@ -42,8 +42,8 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/turboderp-org/exllamav3/releases/download/v0.0.18/exllamav3-0.0.18+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav3/releases/download/v0.0.18/exllamav3-0.0.18+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
diff --git a/requirements/full/requirements_amd.txt b/requirements/full/requirements_amd.txt
index b6b7850d..94367afa 100644
--- a/requirements/full/requirements_amd.txt
+++ b/requirements/full/requirements_amd.txt
@@ -40,7 +40,7 @@ sse-starlette==1.6.5
 tiktoken
 
 # AMD wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+rocm6.4.4-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+rocm6.4.4-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+rocm6.2.4.torch2.6.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
diff --git a/requirements/full/requirements_amd_noavx2.txt b/requirements/full/requirements_amd_noavx2.txt
index e1b0823c..105ac7da 100644
--- a/requirements/full/requirements_amd_noavx2.txt
+++ b/requirements/full/requirements_amd_noavx2.txt
@@ -40,7 +40,7 @@ sse-starlette==1.6.5
 tiktoken
 
 # AMD wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+rocm6.2.4.torch2.6.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
diff --git a/requirements/full/requirements_apple_intel.txt b/requirements/full/requirements_apple_intel.txt
index 08abd111..8ffad947 100644
--- a/requirements/full/requirements_apple_intel.txt
+++ b/requirements/full/requirements_apple_intel.txt
@@ -40,5 +40,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
diff --git a/requirements/full/requirements_apple_silicon.txt b/requirements/full/requirements_apple_silicon.txt
index 6cc0c40e..b6f088c2 100644
--- a/requirements/full/requirements_apple_silicon.txt
+++ b/requirements/full/requirements_apple_silicon.txt
@@ -40,5 +40,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0-py3-none-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0-py3-none-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
diff --git a/requirements/full/requirements_cpu_only.txt b/requirements/full/requirements_cpu_only.txt
index 7b851307..63c63b04 100644
--- a/requirements/full/requirements_cpu_only.txt
+++ b/requirements/full/requirements_cpu_only.txt
@@ -40,5 +40,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # llama.cpp (CPU only, AVX2)
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows"
diff --git a/requirements/full/requirements_cpu_only_noavx2.txt b/requirements/full/requirements_cpu_only_noavx2.txt
index 6f7b5e15..198cad4c 100644
--- a/requirements/full/requirements_cpu_only_noavx2.txt
+++ b/requirements/full/requirements_cpu_only_noavx2.txt
@@ -40,5 +40,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # llama.cpp (CPU only, no AVX2)
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"
diff --git a/requirements/full/requirements_noavx2.txt b/requirements/full/requirements_noavx2.txt
index 7f9e1162..b0da97c6 100644
--- a/requirements/full/requirements_noavx2.txt
+++ b/requirements/full/requirements_noavx2.txt
@@ -42,8 +42,8 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/turboderp-org/exllamav3/releases/download/v0.0.18/exllamav3-0.0.18+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav3/releases/download/v0.0.18/exllamav3-0.0.18+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
diff --git a/requirements/portable/requirements.txt b/requirements/portable/requirements.txt
index 91a2c60b..2007e968 100644
--- a/requirements/portable/requirements.txt
+++ b/requirements/portable/requirements.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
diff --git a/requirements/portable/requirements_amd.txt b/requirements/portable/requirements_amd.txt
index b8d55d3a..b8dd5a2d 100644
--- a/requirements/portable/requirements_amd.txt
+++ b/requirements/portable/requirements_amd.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # AMD wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+rocm6.4.4-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+rocm6.4.4-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
diff --git a/requirements/portable/requirements_amd_noavx2.txt b/requirements/portable/requirements_amd_noavx2.txt
index 296e8b2e..fc26d632 100644
--- a/requirements/portable/requirements_amd_noavx2.txt
+++ b/requirements/portable/requirements_amd_noavx2.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # AMD wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+rocm6.4.4avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+rocm6.4.4avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
diff --git a/requirements/portable/requirements_apple_intel.txt b/requirements/portable/requirements_apple_intel.txt
index 50fd898d..7fab39b4 100644
--- a/requirements/portable/requirements_apple_intel.txt
+++ b/requirements/portable/requirements_apple_intel.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
diff --git a/requirements/portable/requirements_apple_silicon.txt b/requirements/portable/requirements_apple_silicon.txt
index e7268b09..24658d3e 100644
--- a/requirements/portable/requirements_apple_silicon.txt
+++ b/requirements/portable/requirements_apple_silicon.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0-py3-none-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0-py3-none-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
diff --git a/requirements/portable/requirements_cpu_only.txt b/requirements/portable/requirements_cpu_only.txt
index b7d99339..8434463d 100644
--- a/requirements/portable/requirements_cpu_only.txt
+++ b/requirements/portable/requirements_cpu_only.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # llama.cpp (CPU only, AVX2)
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows"
diff --git a/requirements/portable/requirements_cpu_only_noavx2.txt b/requirements/portable/requirements_cpu_only_noavx2.txt
index 043d9db5..c0b8c610 100644
--- a/requirements/portable/requirements_cpu_only_noavx2.txt
+++ b/requirements/portable/requirements_cpu_only_noavx2.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # llama.cpp (CPU only, no AVX2)
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"
diff --git a/requirements/portable/requirements_noavx2.txt b/requirements/portable/requirements_noavx2.txt
index 341f8f45..27817fda 100644
--- a/requirements/portable/requirements_noavx2.txt
+++ b/requirements/portable/requirements_noavx2.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
diff --git a/requirements/portable/requirements_vulkan.txt b/requirements/portable/requirements_vulkan.txt
index 6a69a824..298d9815 100644
--- a/requirements/portable/requirements_vulkan.txt
+++ b/requirements/portable/requirements_vulkan.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # Vulkan wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
diff --git a/requirements/portable/requirements_vulkan_noavx2.txt b/requirements/portable/requirements_vulkan_noavx2.txt
index 2df6df01..f7b78b30 100644
--- a/requirements/portable/requirements_vulkan_noavx2.txt
+++ b/requirements/portable/requirements_vulkan_noavx2.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

From 36747cf99ca1987f56dea2314d8640f311124339 Mon Sep 17 00:00:00 2001
From: oobabooga <112222186+oobabooga@users.noreply.github.com>
Date: Tue, 6 Jan 2026 10:24:34 -0800
Subject: [PATCH 06/11] Lint

---
 css/html_instruct_style.css | 2 +-
 css/main.css                | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/css/html_instruct_style.css b/css/html_instruct_style.css
index a7532cf6..72a148c3 100644
--- a/css/html_instruct_style.css
+++ b/css/html_instruct_style.css
@@ -26,7 +26,7 @@
 
 .dark .chat .message-body :is(th, td),
 .dark .prose hr {
-    border-color: rgba(255, 255, 255, 0.3) !important;
+    border-color: rgb(255 255 255 / 30%) !important;
 }
 
 .chat .message-body :is(p, ul, ol) {
diff --git a/css/main.css b/css/main.css
index 376cfa6d..ecf8568f 100644
--- a/css/main.css
+++ b/css/main.css
@@ -1799,11 +1799,11 @@ button#swap-height-width {
 }
 
 table {
-  border-collapse: collapse;
+    border-collapse: collapse;
 }
 
 table, tr, td, th, thead {
-  border: 0;
+    border: 0;
 }
 
 td + td,

From b0968ed8b493b47d030cf5eede95a0c226b05b2d Mon Sep 17 00:00:00 2001
From: oobabooga <112222186+oobabooga@users.noreply.github.com>
Date: Tue, 6 Jan 2026 10:26:43 -0800
Subject: [PATCH 07/11] Update flash-linear-attention

---
 requirements/full/requirements.txt        | 2 +-
 requirements/full/requirements_noavx2.txt | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/requirements/full/requirements.txt b/requirements/full/requirements.txt
index a7d3403f..edc4f32b 100644
--- a/requirements/full/requirements.txt
+++ b/requirements/full/requirements.txt
@@ -6,7 +6,7 @@ datasets
 diffusers==0.36.*
 einops
 fastapi==0.112.4
-flash-linear-attention==0.4.0
+flash-linear-attention==0.4.*
 html2text==2025.4.15
 huggingface-hub==0.36.0
 jinja2==3.1.6
diff --git a/requirements/full/requirements_noavx2.txt b/requirements/full/requirements_noavx2.txt
index b0da97c6..49b7041f 100644
--- a/requirements/full/requirements_noavx2.txt
+++ b/requirements/full/requirements_noavx2.txt
@@ -6,7 +6,7 @@ datasets
 diffusers==0.36.*
 einops
 fastapi==0.112.4
-flash-linear-attention==0.4.0
+flash-linear-attention==0.4.*
 html2text==2025.4.15
 huggingface-hub==0.36.0
 jinja2==3.1.6

From 45fbec03202c642b01ac71e5b57e855f498bc727 Mon Sep 17 00:00:00 2001
From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com>
Date: Tue, 6 Jan 2026 15:27:10 -0300
Subject: [PATCH 08/11] Update torchao requirement in /requirements/full
 (#7356)

---
 requirements/full/requirements.txt                 | 2 +-
 requirements/full/requirements_amd.txt             | 2 +-
 requirements/full/requirements_amd_noavx2.txt      | 2 +-
 requirements/full/requirements_apple_intel.txt     | 2 +-
 requirements/full/requirements_apple_silicon.txt   | 2 +-
 requirements/full/requirements_cpu_only.txt        | 2 +-
 requirements/full/requirements_cpu_only_noavx2.txt | 2 +-
 requirements/full/requirements_noavx2.txt          | 2 +-
 requirements/full/requirements_nowheels.txt        | 2 +-
 9 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/requirements/full/requirements.txt b/requirements/full/requirements.txt
index edc4f32b..43c71aa9 100644
--- a/requirements/full/requirements.txt
+++ b/requirements/full/requirements.txt
@@ -26,7 +26,7 @@ safetensors==0.7.*
 scipy
 sentencepiece
 tensorboard
-torchao==0.14.*
+torchao==0.15.*
 transformers==4.57.*
 triton-windows==3.5.1.post22; platform_system == "Windows"
 tqdm
diff --git a/requirements/full/requirements_amd.txt b/requirements/full/requirements_amd.txt
index 94367afa..e5d904e1 100644
--- a/requirements/full/requirements_amd.txt
+++ b/requirements/full/requirements_amd.txt
@@ -24,7 +24,7 @@ safetensors==0.7.*
 scipy
 sentencepiece
 tensorboard
-torchao==0.14.*
+torchao==0.15.*
 transformers==4.57.*
 triton-windows==3.5.1.post22; platform_system == "Windows"
 tqdm
diff --git a/requirements/full/requirements_amd_noavx2.txt b/requirements/full/requirements_amd_noavx2.txt
index 105ac7da..75094d2f 100644
--- a/requirements/full/requirements_amd_noavx2.txt
+++ b/requirements/full/requirements_amd_noavx2.txt
@@ -24,7 +24,7 @@ safetensors==0.7.*
 scipy
 sentencepiece
 tensorboard
-torchao==0.14.*
+torchao==0.15.*
 transformers==4.57.*
 triton-windows==3.5.1.post22; platform_system == "Windows"
 tqdm
diff --git a/requirements/full/requirements_apple_intel.txt b/requirements/full/requirements_apple_intel.txt
index 8ffad947..751c38d2 100644
--- a/requirements/full/requirements_apple_intel.txt
+++ b/requirements/full/requirements_apple_intel.txt
@@ -24,7 +24,7 @@ safetensors==0.7.*
 scipy
 sentencepiece
 tensorboard
-torchao==0.14.*
+torchao==0.15.*
 transformers==4.57.*
 triton-windows==3.5.1.post22; platform_system == "Windows"
 tqdm
diff --git a/requirements/full/requirements_apple_silicon.txt b/requirements/full/requirements_apple_silicon.txt
index b6f088c2..6cf2731d 100644
--- a/requirements/full/requirements_apple_silicon.txt
+++ b/requirements/full/requirements_apple_silicon.txt
@@ -24,7 +24,7 @@ safetensors==0.7.*
 scipy
 sentencepiece
 tensorboard
-torchao==0.14.*
+torchao==0.15.*
 transformers==4.57.*
 triton-windows==3.5.1.post22; platform_system == "Windows"
 tqdm
diff --git a/requirements/full/requirements_cpu_only.txt b/requirements/full/requirements_cpu_only.txt
index 63c63b04..c02d6250 100644
--- a/requirements/full/requirements_cpu_only.txt
+++ b/requirements/full/requirements_cpu_only.txt
@@ -24,7 +24,7 @@ safetensors==0.7.*
 scipy
 sentencepiece
 tensorboard
-torchao==0.14.*
+torchao==0.15.*
 transformers==4.57.*
 triton-windows==3.5.1.post22; platform_system == "Windows"
 tqdm
diff --git a/requirements/full/requirements_cpu_only_noavx2.txt b/requirements/full/requirements_cpu_only_noavx2.txt
index 198cad4c..88464eab 100644
--- a/requirements/full/requirements_cpu_only_noavx2.txt
+++ b/requirements/full/requirements_cpu_only_noavx2.txt
@@ -24,7 +24,7 @@ safetensors==0.7.*
 scipy
 sentencepiece
 tensorboard
-torchao==0.14.*
+torchao==0.15.*
 transformers==4.57.*
 triton-windows==3.5.1.post22; platform_system == "Windows"
 tqdm
diff --git a/requirements/full/requirements_noavx2.txt b/requirements/full/requirements_noavx2.txt
index 49b7041f..d842f85c 100644
--- a/requirements/full/requirements_noavx2.txt
+++ b/requirements/full/requirements_noavx2.txt
@@ -26,7 +26,7 @@ safetensors==0.7.*
 scipy
 sentencepiece
 tensorboard
-torchao==0.14.*
+torchao==0.15.*
 transformers==4.57.*
 triton-windows==3.5.1.post22; platform_system == "Windows"
 tqdm
diff --git a/requirements/full/requirements_nowheels.txt b/requirements/full/requirements_nowheels.txt
index 070e5fd0..d8d7a927 100644
--- a/requirements/full/requirements_nowheels.txt
+++ b/requirements/full/requirements_nowheels.txt
@@ -24,7 +24,7 @@ safetensors==0.7.*
 scipy
 sentencepiece
 tensorboard
-torchao==0.14.*
+torchao==0.15.*
 transformers==4.57.*
 triton-windows==3.5.1.post22; platform_system == "Windows"
 tqdm

From 50a35b483c30fb91664877a0aa031228b8e8f3d3 Mon Sep 17 00:00:00 2001
From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com>
Date: Tue, 6 Jan 2026 15:27:23 -0300
Subject: [PATCH 09/11] Update bitsandbytes requirement in /requirements/full
 (#7353)

---
 requirements/full/requirements.txt        | 2 +-
 requirements/full/requirements_noavx2.txt | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/requirements/full/requirements.txt b/requirements/full/requirements.txt
index 43c71aa9..b97ccd62 100644
--- a/requirements/full/requirements.txt
+++ b/requirements/full/requirements.txt
@@ -1,6 +1,6 @@
 accelerate==1.8.*
 audioop-lts<1.0; python_version >= "3.13"
-bitsandbytes==0.48.*
+bitsandbytes==0.49.*
 colorama
 datasets
 diffusers==0.36.*
diff --git a/requirements/full/requirements_noavx2.txt b/requirements/full/requirements_noavx2.txt
index d842f85c..34492c64 100644
--- a/requirements/full/requirements_noavx2.txt
+++ b/requirements/full/requirements_noavx2.txt
@@ -1,6 +1,6 @@
 accelerate==1.8.*
 audioop-lts<1.0; python_version >= "3.13"
-bitsandbytes==0.48.*
+bitsandbytes==0.49.*
 colorama
 datasets
 diffusers==0.36.*

From 332fd40653b57a3a515143f5684620c49075e837 Mon Sep 17 00:00:00 2001
From: oobabooga <112222186+oobabooga@users.noreply.github.com>
Date: Wed, 7 Jan 2026 19:06:23 -0800
Subject: [PATCH 10/11] Update llama.cpp

---
 requirements/full/requirements.txt                     | 4 ++--
 requirements/full/requirements_amd.txt                 | 4 ++--
 requirements/full/requirements_amd_noavx2.txt          | 4 ++--
 requirements/full/requirements_apple_intel.txt         | 4 ++--
 requirements/full/requirements_apple_silicon.txt       | 4 ++--
 requirements/full/requirements_cpu_only.txt            | 4 ++--
 requirements/full/requirements_cpu_only_noavx2.txt     | 4 ++--
 requirements/full/requirements_noavx2.txt              | 4 ++--
 requirements/portable/requirements.txt                 | 4 ++--
 requirements/portable/requirements_amd.txt             | 4 ++--
 requirements/portable/requirements_amd_noavx2.txt      | 4 ++--
 requirements/portable/requirements_apple_intel.txt     | 4 ++--
 requirements/portable/requirements_apple_silicon.txt   | 4 ++--
 requirements/portable/requirements_cpu_only.txt        | 4 ++--
 requirements/portable/requirements_cpu_only_noavx2.txt | 4 ++--
 requirements/portable/requirements_noavx2.txt          | 4 ++--
 requirements/portable/requirements_vulkan.txt          | 4 ++--
 requirements/portable/requirements_vulkan_noavx2.txt   | 4 ++--
 18 files changed, 36 insertions(+), 36 deletions(-)

diff --git a/requirements/full/requirements.txt b/requirements/full/requirements.txt
index b97ccd62..2ee917c6 100644
--- a/requirements/full/requirements.txt
+++ b/requirements/full/requirements.txt
@@ -42,8 +42,8 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/turboderp-org/exllamav3/releases/download/v0.0.18/exllamav3-0.0.18+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav3/releases/download/v0.0.18/exllamav3-0.0.18+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
diff --git a/requirements/full/requirements_amd.txt b/requirements/full/requirements_amd.txt
index e5d904e1..bd3a9c0b 100644
--- a/requirements/full/requirements_amd.txt
+++ b/requirements/full/requirements_amd.txt
@@ -40,7 +40,7 @@ sse-starlette==1.6.5
 tiktoken
 
 # AMD wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+rocm6.4.4-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+rocm6.4.4-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+rocm6.2.4.torch2.6.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
diff --git a/requirements/full/requirements_amd_noavx2.txt b/requirements/full/requirements_amd_noavx2.txt
index 75094d2f..b20112ec 100644
--- a/requirements/full/requirements_amd_noavx2.txt
+++ b/requirements/full/requirements_amd_noavx2.txt
@@ -40,7 +40,7 @@ sse-starlette==1.6.5
 tiktoken
 
 # AMD wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+rocm6.2.4.torch2.6.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
diff --git a/requirements/full/requirements_apple_intel.txt b/requirements/full/requirements_apple_intel.txt
index 751c38d2..f4e94577 100644
--- a/requirements/full/requirements_apple_intel.txt
+++ b/requirements/full/requirements_apple_intel.txt
@@ -40,5 +40,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
diff --git a/requirements/full/requirements_apple_silicon.txt b/requirements/full/requirements_apple_silicon.txt
index 6cf2731d..710d055c 100644
--- a/requirements/full/requirements_apple_silicon.txt
+++ b/requirements/full/requirements_apple_silicon.txt
@@ -40,5 +40,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0-py3-none-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0-py3-none-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
diff --git a/requirements/full/requirements_cpu_only.txt b/requirements/full/requirements_cpu_only.txt
index c02d6250..890486bf 100644
--- a/requirements/full/requirements_cpu_only.txt
+++ b/requirements/full/requirements_cpu_only.txt
@@ -40,5 +40,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # llama.cpp (CPU only, AVX2)
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows"
diff --git a/requirements/full/requirements_cpu_only_noavx2.txt b/requirements/full/requirements_cpu_only_noavx2.txt
index 88464eab..d50bfb47 100644
--- a/requirements/full/requirements_cpu_only_noavx2.txt
+++ b/requirements/full/requirements_cpu_only_noavx2.txt
@@ -40,5 +40,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # llama.cpp (CPU only, no AVX2)
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"
diff --git a/requirements/full/requirements_noavx2.txt b/requirements/full/requirements_noavx2.txt
index 34492c64..88a1f3e4 100644
--- a/requirements/full/requirements_noavx2.txt
+++ b/requirements/full/requirements_noavx2.txt
@@ -42,8 +42,8 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/turboderp-org/exllamav3/releases/download/v0.0.18/exllamav3-0.0.18+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav3/releases/download/v0.0.18/exllamav3-0.0.18+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
diff --git a/requirements/portable/requirements.txt b/requirements/portable/requirements.txt
index 2007e968..3da1bbdd 100644
--- a/requirements/portable/requirements.txt
+++ b/requirements/portable/requirements.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
diff --git a/requirements/portable/requirements_amd.txt b/requirements/portable/requirements_amd.txt
index b8dd5a2d..10c3fb33 100644
--- a/requirements/portable/requirements_amd.txt
+++ b/requirements/portable/requirements_amd.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # AMD wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+rocm6.4.4-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+rocm6.4.4-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
diff --git a/requirements/portable/requirements_amd_noavx2.txt b/requirements/portable/requirements_amd_noavx2.txt
index fc26d632..c3c16abc 100644
--- a/requirements/portable/requirements_amd_noavx2.txt
+++ b/requirements/portable/requirements_amd_noavx2.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # AMD wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+rocm6.4.4avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+rocm6.4.4avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
diff --git a/requirements/portable/requirements_apple_intel.txt b/requirements/portable/requirements_apple_intel.txt
index 7fab39b4..adf154c5 100644
--- a/requirements/portable/requirements_apple_intel.txt
+++ b/requirements/portable/requirements_apple_intel.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
diff --git a/requirements/portable/requirements_apple_silicon.txt b/requirements/portable/requirements_apple_silicon.txt
index 24658d3e..cbd9e999 100644
--- a/requirements/portable/requirements_apple_silicon.txt
+++ b/requirements/portable/requirements_apple_silicon.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0-py3-none-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0-py3-none-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
diff --git a/requirements/portable/requirements_cpu_only.txt b/requirements/portable/requirements_cpu_only.txt
index 8434463d..0f39c2e1 100644
--- a/requirements/portable/requirements_cpu_only.txt
+++ b/requirements/portable/requirements_cpu_only.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # llama.cpp (CPU only, AVX2)
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows"
diff --git a/requirements/portable/requirements_cpu_only_noavx2.txt b/requirements/portable/requirements_cpu_only_noavx2.txt
index c0b8c610..64b0688d 100644
--- a/requirements/portable/requirements_cpu_only_noavx2.txt
+++ b/requirements/portable/requirements_cpu_only_noavx2.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # llama.cpp (CPU only, no AVX2)
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"
diff --git a/requirements/portable/requirements_noavx2.txt b/requirements/portable/requirements_noavx2.txt
index 27817fda..b72757cc 100644
--- a/requirements/portable/requirements_noavx2.txt
+++ b/requirements/portable/requirements_noavx2.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
diff --git a/requirements/portable/requirements_vulkan.txt b/requirements/portable/requirements_vulkan.txt
index 298d9815..8cc9d776 100644
--- a/requirements/portable/requirements_vulkan.txt
+++ b/requirements/portable/requirements_vulkan.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # Vulkan wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
diff --git a/requirements/portable/requirements_vulkan_noavx2.txt b/requirements/portable/requirements_vulkan_noavx2.txt
index f7b78b30..25ec67cd 100644
--- a/requirements/portable/requirements_vulkan_noavx2.txt
+++ b/requirements/portable/requirements_vulkan_noavx2.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.72.0/llama_cpp_binaries-0.72.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

From d79cdc614cb93e4687abf16eafda24c0351cbbf0 Mon Sep 17 00:00:00 2001
From: oobabooga <112222186+oobabooga@users.noreply.github.com>
Date: Thu, 8 Jan 2026 11:24:15 -0800
Subject: [PATCH 11/11] Update llama.cpp

---
 requirements/full/requirements.txt                     | 4 ++--
 requirements/full/requirements_amd.txt                 | 4 ++--
 requirements/full/requirements_amd_noavx2.txt          | 4 ++--
 requirements/full/requirements_apple_intel.txt         | 4 ++--
 requirements/full/requirements_apple_silicon.txt       | 4 ++--
 requirements/full/requirements_cpu_only.txt            | 4 ++--
 requirements/full/requirements_cpu_only_noavx2.txt     | 4 ++--
 requirements/full/requirements_noavx2.txt              | 4 ++--
 requirements/portable/requirements.txt                 | 4 ++--
 requirements/portable/requirements_amd.txt             | 4 ++--
 requirements/portable/requirements_amd_noavx2.txt      | 4 ++--
 requirements/portable/requirements_apple_intel.txt     | 4 ++--
 requirements/portable/requirements_apple_silicon.txt   | 4 ++--
 requirements/portable/requirements_cpu_only.txt        | 4 ++--
 requirements/portable/requirements_cpu_only_noavx2.txt | 4 ++--
 requirements/portable/requirements_noavx2.txt          | 4 ++--
 requirements/portable/requirements_vulkan.txt          | 4 ++--
 requirements/portable/requirements_vulkan_noavx2.txt   | 4 ++--
 18 files changed, 36 insertions(+), 36 deletions(-)

diff --git a/requirements/full/requirements.txt b/requirements/full/requirements.txt
index 2ee917c6..1bc9ad1b 100644
--- a/requirements/full/requirements.txt
+++ b/requirements/full/requirements.txt
@@ -42,8 +42,8 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/turboderp-org/exllamav3/releases/download/v0.0.18/exllamav3-0.0.18+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav3/releases/download/v0.0.18/exllamav3-0.0.18+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
diff --git a/requirements/full/requirements_amd.txt b/requirements/full/requirements_amd.txt
index bd3a9c0b..9b0fa12e 100644
--- a/requirements/full/requirements_amd.txt
+++ b/requirements/full/requirements_amd.txt
@@ -40,7 +40,7 @@ sse-starlette==1.6.5
 tiktoken
 
 # AMD wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+rocm6.4.4-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+rocm6.4.4-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+rocm6.2.4.torch2.6.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
diff --git a/requirements/full/requirements_amd_noavx2.txt b/requirements/full/requirements_amd_noavx2.txt
index b20112ec..60a54157 100644
--- a/requirements/full/requirements_amd_noavx2.txt
+++ b/requirements/full/requirements_amd_noavx2.txt
@@ -40,7 +40,7 @@ sse-starlette==1.6.5
 tiktoken
 
 # AMD wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+rocm6.2.4.torch2.6.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
diff --git a/requirements/full/requirements_apple_intel.txt b/requirements/full/requirements_apple_intel.txt
index f4e94577..c97928f9 100644
--- a/requirements/full/requirements_apple_intel.txt
+++ b/requirements/full/requirements_apple_intel.txt
@@ -40,5 +40,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
diff --git a/requirements/full/requirements_apple_silicon.txt b/requirements/full/requirements_apple_silicon.txt
index 710d055c..c671c4d9 100644
--- a/requirements/full/requirements_apple_silicon.txt
+++ b/requirements/full/requirements_apple_silicon.txt
@@ -40,5 +40,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0-py3-none-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0-py3-none-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
diff --git a/requirements/full/requirements_cpu_only.txt b/requirements/full/requirements_cpu_only.txt
index 890486bf..1a14d0ae 100644
--- a/requirements/full/requirements_cpu_only.txt
+++ b/requirements/full/requirements_cpu_only.txt
@@ -40,5 +40,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # llama.cpp (CPU only, AVX2)
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows"
diff --git a/requirements/full/requirements_cpu_only_noavx2.txt b/requirements/full/requirements_cpu_only_noavx2.txt
index d50bfb47..2a9484bf 100644
--- a/requirements/full/requirements_cpu_only_noavx2.txt
+++ b/requirements/full/requirements_cpu_only_noavx2.txt
@@ -40,5 +40,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # llama.cpp (CPU only, no AVX2)
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"
diff --git a/requirements/full/requirements_noavx2.txt b/requirements/full/requirements_noavx2.txt
index 88a1f3e4..1e75b791 100644
--- a/requirements/full/requirements_noavx2.txt
+++ b/requirements/full/requirements_noavx2.txt
@@ -42,8 +42,8 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/turboderp-org/exllamav3/releases/download/v0.0.18/exllamav3-0.0.18+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav3/releases/download/v0.0.18/exllamav3-0.0.18+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
diff --git a/requirements/portable/requirements.txt b/requirements/portable/requirements.txt
index 3da1bbdd..2f6bf511 100644
--- a/requirements/portable/requirements.txt
+++ b/requirements/portable/requirements.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
diff --git a/requirements/portable/requirements_amd.txt b/requirements/portable/requirements_amd.txt
index 10c3fb33..209610ce 100644
--- a/requirements/portable/requirements_amd.txt
+++ b/requirements/portable/requirements_amd.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # AMD wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+rocm6.4.4-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+rocm6.4.4-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
diff --git a/requirements/portable/requirements_amd_noavx2.txt b/requirements/portable/requirements_amd_noavx2.txt
index c3c16abc..29a1f72b 100644
--- a/requirements/portable/requirements_amd_noavx2.txt
+++ b/requirements/portable/requirements_amd_noavx2.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # AMD wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+rocm6.4.4avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+rocm6.4.4avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
diff --git a/requirements/portable/requirements_apple_intel.txt b/requirements/portable/requirements_apple_intel.txt
index adf154c5..8812ac39 100644
--- a/requirements/portable/requirements_apple_intel.txt
+++ b/requirements/portable/requirements_apple_intel.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
diff --git a/requirements/portable/requirements_apple_silicon.txt b/requirements/portable/requirements_apple_silicon.txt
index cbd9e999..c627cfd4 100644
--- a/requirements/portable/requirements_apple_silicon.txt
+++ b/requirements/portable/requirements_apple_silicon.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0-py3-none-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0-py3-none-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
diff --git a/requirements/portable/requirements_cpu_only.txt b/requirements/portable/requirements_cpu_only.txt
index 0f39c2e1..5ca660ad 100644
--- a/requirements/portable/requirements_cpu_only.txt
+++ b/requirements/portable/requirements_cpu_only.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # llama.cpp (CPU only, AVX2)
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows"
diff --git a/requirements/portable/requirements_cpu_only_noavx2.txt b/requirements/portable/requirements_cpu_only_noavx2.txt
index 64b0688d..5bb282eb 100644
--- a/requirements/portable/requirements_cpu_only_noavx2.txt
+++ b/requirements/portable/requirements_cpu_only_noavx2.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # llama.cpp (CPU only, no AVX2)
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"
diff --git a/requirements/portable/requirements_noavx2.txt b/requirements/portable/requirements_noavx2.txt
index b72757cc..ecce4a2f 100644
--- a/requirements/portable/requirements_noavx2.txt
+++ b/requirements/portable/requirements_noavx2.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
diff --git a/requirements/portable/requirements_vulkan.txt b/requirements/portable/requirements_vulkan.txt
index 8cc9d776..4b3adddc 100644
--- a/requirements/portable/requirements_vulkan.txt
+++ b/requirements/portable/requirements_vulkan.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # Vulkan wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
diff --git a/requirements/portable/requirements_vulkan_noavx2.txt b/requirements/portable/requirements_vulkan_noavx2.txt
index 25ec67cd..8d6acdd7 100644
--- a/requirements/portable/requirements_vulkan_noavx2.txt
+++ b/requirements/portable/requirements_vulkan_noavx2.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.73.0/llama_cpp_binaries-0.73.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"