From c4ebab9b29e4df06e61e526f3328d24b0fee2fc8 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Mon, 8 Dec 2025 17:56:07 -0300 Subject: [PATCH 1/5] Bump triton-windows in /requirements/full (#7346) --- 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 64910090..482406c9 100644 --- a/requirements/full/requirements.txt +++ b/requirements/full/requirements.txt @@ -28,7 +28,7 @@ sentencepiece tensorboard torchao==0.14.* transformers==4.57.* -triton-windows==3.5.1.post21; platform_system == "Windows" +triton-windows==3.5.1.post22; platform_system == "Windows" tqdm wandb diff --git a/requirements/full/requirements_amd.txt b/requirements/full/requirements_amd.txt index 5a3d417c..e8b6c971 100644 --- a/requirements/full/requirements_amd.txt +++ b/requirements/full/requirements_amd.txt @@ -26,7 +26,7 @@ sentencepiece tensorboard torchao==0.14.* transformers==4.57.* -triton-windows==3.5.1.post21; platform_system == "Windows" +triton-windows==3.5.1.post22; platform_system == "Windows" tqdm wandb diff --git a/requirements/full/requirements_amd_noavx2.txt b/requirements/full/requirements_amd_noavx2.txt index 4ff947c1..add4c2b8 100644 --- a/requirements/full/requirements_amd_noavx2.txt +++ b/requirements/full/requirements_amd_noavx2.txt @@ -26,7 +26,7 @@ sentencepiece tensorboard torchao==0.14.* transformers==4.57.* -triton-windows==3.5.1.post21; platform_system == "Windows" +triton-windows==3.5.1.post22; platform_system == "Windows" tqdm wandb diff --git a/requirements/full/requirements_apple_intel.txt b/requirements/full/requirements_apple_intel.txt index 47cacfeb..3f0c6f8d 100644 --- a/requirements/full/requirements_apple_intel.txt +++ b/requirements/full/requirements_apple_intel.txt @@ -26,7 +26,7 @@ sentencepiece tensorboard torchao==0.14.* transformers==4.57.* -triton-windows==3.5.1.post21; platform_system == "Windows" +triton-windows==3.5.1.post22; platform_system == "Windows" tqdm wandb diff --git a/requirements/full/requirements_apple_silicon.txt b/requirements/full/requirements_apple_silicon.txt index 51d4aa4f..dbebc6d4 100644 --- a/requirements/full/requirements_apple_silicon.txt +++ b/requirements/full/requirements_apple_silicon.txt @@ -26,7 +26,7 @@ sentencepiece tensorboard torchao==0.14.* transformers==4.57.* -triton-windows==3.5.1.post21; platform_system == "Windows" +triton-windows==3.5.1.post22; platform_system == "Windows" tqdm wandb diff --git a/requirements/full/requirements_cpu_only.txt b/requirements/full/requirements_cpu_only.txt index 0b465964..436e2ede 100644 --- a/requirements/full/requirements_cpu_only.txt +++ b/requirements/full/requirements_cpu_only.txt @@ -26,7 +26,7 @@ sentencepiece tensorboard torchao==0.14.* transformers==4.57.* -triton-windows==3.5.1.post21; platform_system == "Windows" +triton-windows==3.5.1.post22; platform_system == "Windows" tqdm wandb diff --git a/requirements/full/requirements_cpu_only_noavx2.txt b/requirements/full/requirements_cpu_only_noavx2.txt index 50363814..cc77f762 100644 --- a/requirements/full/requirements_cpu_only_noavx2.txt +++ b/requirements/full/requirements_cpu_only_noavx2.txt @@ -26,7 +26,7 @@ sentencepiece tensorboard torchao==0.14.* transformers==4.57.* -triton-windows==3.5.1.post21; platform_system == "Windows" +triton-windows==3.5.1.post22; platform_system == "Windows" tqdm wandb diff --git a/requirements/full/requirements_noavx2.txt b/requirements/full/requirements_noavx2.txt index 0c6f6255..02ac4b17 100644 --- a/requirements/full/requirements_noavx2.txt +++ b/requirements/full/requirements_noavx2.txt @@ -28,7 +28,7 @@ sentencepiece tensorboard torchao==0.14.* transformers==4.57.* -triton-windows==3.5.1.post21; platform_system == "Windows" +triton-windows==3.5.1.post22; platform_system == "Windows" tqdm wandb diff --git a/requirements/full/requirements_nowheels.txt b/requirements/full/requirements_nowheels.txt index ee8fc045..bfb8934f 100644 --- a/requirements/full/requirements_nowheels.txt +++ b/requirements/full/requirements_nowheels.txt @@ -26,7 +26,7 @@ sentencepiece tensorboard torchao==0.14.* transformers==4.57.* -triton-windows==3.5.1.post21; platform_system == "Windows" +triton-windows==3.5.1.post22; platform_system == "Windows" tqdm wandb From 85269d7fbbb02633692727a5f7b228067ba507eb Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Mon, 8 Dec 2025 17:58:27 -0300 Subject: [PATCH 2/5] Update safetensors requirement in /requirements/full (#7323) --- 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 482406c9..bde3b6a3 100644 --- a/requirements/full/requirements.txt +++ b/requirements/full/requirements.txt @@ -22,7 +22,7 @@ python-docx==1.1.2 pyyaml requests rich -safetensors==0.6.* +safetensors==0.7.* scipy sentencepiece tensorboard diff --git a/requirements/full/requirements_amd.txt b/requirements/full/requirements_amd.txt index e8b6c971..716a2404 100644 --- a/requirements/full/requirements_amd.txt +++ b/requirements/full/requirements_amd.txt @@ -20,7 +20,7 @@ python-docx==1.1.2 pyyaml requests rich -safetensors==0.6.* +safetensors==0.7.* scipy sentencepiece tensorboard diff --git a/requirements/full/requirements_amd_noavx2.txt b/requirements/full/requirements_amd_noavx2.txt index add4c2b8..5c335493 100644 --- a/requirements/full/requirements_amd_noavx2.txt +++ b/requirements/full/requirements_amd_noavx2.txt @@ -20,7 +20,7 @@ python-docx==1.1.2 pyyaml requests rich -safetensors==0.6.* +safetensors==0.7.* scipy sentencepiece tensorboard diff --git a/requirements/full/requirements_apple_intel.txt b/requirements/full/requirements_apple_intel.txt index 3f0c6f8d..3aa4a6f8 100644 --- a/requirements/full/requirements_apple_intel.txt +++ b/requirements/full/requirements_apple_intel.txt @@ -20,7 +20,7 @@ python-docx==1.1.2 pyyaml requests rich -safetensors==0.6.* +safetensors==0.7.* scipy sentencepiece tensorboard diff --git a/requirements/full/requirements_apple_silicon.txt b/requirements/full/requirements_apple_silicon.txt index dbebc6d4..400050b6 100644 --- a/requirements/full/requirements_apple_silicon.txt +++ b/requirements/full/requirements_apple_silicon.txt @@ -20,7 +20,7 @@ python-docx==1.1.2 pyyaml requests rich -safetensors==0.6.* +safetensors==0.7.* scipy sentencepiece tensorboard diff --git a/requirements/full/requirements_cpu_only.txt b/requirements/full/requirements_cpu_only.txt index 436e2ede..84722416 100644 --- a/requirements/full/requirements_cpu_only.txt +++ b/requirements/full/requirements_cpu_only.txt @@ -20,7 +20,7 @@ python-docx==1.1.2 pyyaml requests rich -safetensors==0.6.* +safetensors==0.7.* scipy sentencepiece tensorboard diff --git a/requirements/full/requirements_cpu_only_noavx2.txt b/requirements/full/requirements_cpu_only_noavx2.txt index cc77f762..0dbc8465 100644 --- a/requirements/full/requirements_cpu_only_noavx2.txt +++ b/requirements/full/requirements_cpu_only_noavx2.txt @@ -20,7 +20,7 @@ python-docx==1.1.2 pyyaml requests rich -safetensors==0.6.* +safetensors==0.7.* scipy sentencepiece tensorboard diff --git a/requirements/full/requirements_noavx2.txt b/requirements/full/requirements_noavx2.txt index 02ac4b17..0691331b 100644 --- a/requirements/full/requirements_noavx2.txt +++ b/requirements/full/requirements_noavx2.txt @@ -22,7 +22,7 @@ python-docx==1.1.2 pyyaml requests rich -safetensors==0.6.* +safetensors==0.7.* scipy sentencepiece tensorboard diff --git a/requirements/full/requirements_nowheels.txt b/requirements/full/requirements_nowheels.txt index bfb8934f..070e5fd0 100644 --- a/requirements/full/requirements_nowheels.txt +++ b/requirements/full/requirements_nowheels.txt @@ -20,7 +20,7 @@ python-docx==1.1.2 pyyaml requests rich -safetensors==0.6.* +safetensors==0.7.* scipy sentencepiece tensorboard From aa16266c389738e3116f5b04818b61404f7d43bd Mon Sep 17 00:00:00 2001 From: oobabooga <112222186+oobabooga@users.noreply.github.com> Date: Tue, 9 Dec 2025 03:19:23 -0800 Subject: [PATCH 3/5] 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 64910090..64273f89 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/v0.66.0/llama_cpp_binaries-0.66.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows" -https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.66.0/llama_cpp_binaries-0.66.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/turboderp-org/exllamav3/releases/download/v0.0.17/exllamav3-0.0.17+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/v0.0.17/exllamav3-0.0.17+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 5a3d417c..756fc4d6 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/v0.66.0/llama_cpp_binaries-0.66.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows" -https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.66.0/llama_cpp_binaries-0.66.0+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/v0.67.0/llama_cpp_binaries-0.67.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+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 4ff947c1..48be84e9 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/v0.66.0/llama_cpp_binaries-0.66.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows" -https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.66.0/llama_cpp_binaries-0.66.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+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 47cacfeb..41e1d8e5 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/v0.66.0/llama_cpp_binaries-0.66.0-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/v0.66.0/llama_cpp_binaries-0.66.0-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/v0.67.0/llama_cpp_binaries-0.67.0-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/v0.67.0/llama_cpp_binaries-0.67.0-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 51d4aa4f..4bd24475 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/v0.66.0/llama_cpp_binaries-0.66.0-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/v0.66.0/llama_cpp_binaries-0.66.0-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/v0.67.0/llama_cpp_binaries-0.67.0-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/v0.67.0/llama_cpp_binaries-0.67.0-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 0b465964..7c308e68 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/v0.66.0/llama_cpp_binaries-0.66.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" -https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.66.0/llama_cpp_binaries-0.66.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+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 50363814..755d57aa 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/v0.66.0/llama_cpp_binaries-0.66.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" -https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.66.0/llama_cpp_binaries-0.66.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows" diff --git a/requirements/full/requirements_noavx2.txt b/requirements/full/requirements_noavx2.txt index 0c6f6255..ae609393 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/v0.66.0/llama_cpp_binaries-0.66.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows" -https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.66.0/llama_cpp_binaries-0.66.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/turboderp-org/exllamav3/releases/download/v0.0.17/exllamav3-0.0.17+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/v0.0.17/exllamav3-0.0.17+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 4a92fb8d..1f9313ed 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/v0.66.0/llama_cpp_binaries-0.66.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows" -https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.66.0/llama_cpp_binaries-0.66.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+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 5ad1fe3a..9d6f10cf 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/v0.66.0/llama_cpp_binaries-0.66.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows" -https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.66.0/llama_cpp_binaries-0.66.0+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/v0.67.0/llama_cpp_binaries-0.67.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+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 9c3e2851..34340e19 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/v0.66.0/llama_cpp_binaries-0.66.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows" -https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.66.0/llama_cpp_binaries-0.66.0+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/v0.67.0/llama_cpp_binaries-0.67.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+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 8a618e35..f95feb27 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/v0.66.0/llama_cpp_binaries-0.66.0-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/v0.66.0/llama_cpp_binaries-0.66.0-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/v0.67.0/llama_cpp_binaries-0.67.0-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/v0.67.0/llama_cpp_binaries-0.67.0-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 c1c643e8..93887a69 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/v0.66.0/llama_cpp_binaries-0.66.0-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/v0.66.0/llama_cpp_binaries-0.66.0-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/v0.67.0/llama_cpp_binaries-0.67.0-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/v0.67.0/llama_cpp_binaries-0.67.0-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 f4bc8cab..f6a17a36 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/v0.66.0/llama_cpp_binaries-0.66.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" -https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.66.0/llama_cpp_binaries-0.66.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+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 81f9bf2e..33f9d3a0 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/v0.66.0/llama_cpp_binaries-0.66.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" -https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.66.0/llama_cpp_binaries-0.66.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows" diff --git a/requirements/portable/requirements_noavx2.txt b/requirements/portable/requirements_noavx2.txt index 6cc87a4e..565eb269 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/v0.66.0/llama_cpp_binaries-0.66.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows" -https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.66.0/llama_cpp_binaries-0.66.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+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 25c3638f..01cd161a 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/v0.66.0/llama_cpp_binaries-0.66.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows" -https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.66.0/llama_cpp_binaries-0.66.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+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 54d0cd1a..ed3016ea 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/v0.66.0/llama_cpp_binaries-0.66.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows" -https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.66.0/llama_cpp_binaries-0.66.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" From 9fe40ff90f2ef5a4dc9f0dff0698376e2b3d4927 Mon Sep 17 00:00:00 2001 From: oobabooga <112222186+oobabooga@users.noreply.github.com> Date: Wed, 10 Dec 2025 05:37:33 -0800 Subject: [PATCH 4/5] Update exllamav3 to 0.0.18 --- requirements/full/requirements.txt | 4 ++-- requirements/full/requirements_noavx2.txt | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/requirements/full/requirements.txt b/requirements/full/requirements.txt index 8ed9b23e..a7a46077 100644 --- a/requirements/full/requirements.txt +++ b/requirements/full/requirements.txt @@ -44,8 +44,8 @@ tiktoken # CUDA wheels https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" -https://github.com/turboderp-org/exllamav3/releases/download/v0.0.17/exllamav3-0.0.17+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/v0.0.17/exllamav3-0.0.17+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/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" https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+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-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64" diff --git a/requirements/full/requirements_noavx2.txt b/requirements/full/requirements_noavx2.txt index d48cd0b6..32068ea8 100644 --- a/requirements/full/requirements_noavx2.txt +++ b/requirements/full/requirements_noavx2.txt @@ -44,8 +44,8 @@ tiktoken # CUDA wheels https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows" https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" -https://github.com/turboderp-org/exllamav3/releases/download/v0.0.17/exllamav3-0.0.17+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/v0.0.17/exllamav3-0.0.17+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/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" https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+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-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64" From 6e8fb0e7b17d5dd9ed35e04ce30f4c35922c8db5 Mon Sep 17 00:00:00 2001 From: oobabooga <112222186+oobabooga@users.noreply.github.com> Date: Sun, 14 Dec 2025 13:32:14 -0800 Subject: [PATCH 5/5] 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 a7a46077..21336c55 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/v0.67.0/llama_cpp_binaries-0.67.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows" -https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+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 6541571a..92e8d66f 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/v0.67.0/llama_cpp_binaries-0.67.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows" -https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+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/v0.70.0/llama_cpp_binaries-0.70.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+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 01b240ee..baf7e66b 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/v0.67.0/llama_cpp_binaries-0.67.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows" -https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+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 dc0479a8..31d7c576 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/v0.67.0/llama_cpp_binaries-0.67.0-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/v0.67.0/llama_cpp_binaries-0.67.0-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/v0.70.0/llama_cpp_binaries-0.70.0-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/v0.70.0/llama_cpp_binaries-0.70.0-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 82de929f..cd0f944e 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/v0.67.0/llama_cpp_binaries-0.67.0-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/v0.67.0/llama_cpp_binaries-0.67.0-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/v0.70.0/llama_cpp_binaries-0.70.0-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/v0.70.0/llama_cpp_binaries-0.70.0-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 3a323aa1..5f591edf 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/v0.67.0/llama_cpp_binaries-0.67.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" -https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+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 8e7a59b9..74f5d3f8 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/v0.67.0/llama_cpp_binaries-0.67.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" -https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows" diff --git a/requirements/full/requirements_noavx2.txt b/requirements/full/requirements_noavx2.txt index 32068ea8..b013150a 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/v0.67.0/llama_cpp_binaries-0.67.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows" -https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+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 1f9313ed..fc7560d9 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/v0.67.0/llama_cpp_binaries-0.67.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows" -https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+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 9d6f10cf..5b64e2a9 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/v0.67.0/llama_cpp_binaries-0.67.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows" -https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+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/v0.70.0/llama_cpp_binaries-0.70.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+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 34340e19..6ec4a89a 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/v0.67.0/llama_cpp_binaries-0.67.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows" -https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+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/v0.70.0/llama_cpp_binaries-0.70.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+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 f95feb27..78ad17da 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/v0.67.0/llama_cpp_binaries-0.67.0-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/v0.67.0/llama_cpp_binaries-0.67.0-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/v0.70.0/llama_cpp_binaries-0.70.0-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/v0.70.0/llama_cpp_binaries-0.70.0-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 93887a69..d8a41ecc 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/v0.67.0/llama_cpp_binaries-0.67.0-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/v0.67.0/llama_cpp_binaries-0.67.0-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/v0.70.0/llama_cpp_binaries-0.70.0-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/v0.70.0/llama_cpp_binaries-0.70.0-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 f6a17a36..68fe0ee7 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/v0.67.0/llama_cpp_binaries-0.67.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" -https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+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 33f9d3a0..a8a5b87d 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/v0.67.0/llama_cpp_binaries-0.67.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" -https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows" diff --git a/requirements/portable/requirements_noavx2.txt b/requirements/portable/requirements_noavx2.txt index 565eb269..ccf57891 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/v0.67.0/llama_cpp_binaries-0.67.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows" -https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+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 01cd161a..5fb6bb70 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/v0.67.0/llama_cpp_binaries-0.67.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows" -https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+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 ed3016ea..b99bd558 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/v0.67.0/llama_cpp_binaries-0.67.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows" -https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.67.0/llama_cpp_binaries-0.67.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows" +https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.70.0/llama_cpp_binaries-0.70.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"