diff --git a/README.md b/README.md
index c3f7d8a6..d350d959 100644
--- a/README.md
+++ b/README.md
@@ -164,7 +164,7 @@ conda install -y -c "nvidia/label/cuda-12.8.1" cuda
 ```
 git clone https://github.com/oobabooga/text-generation-webui
 cd text-generation-webui
-pip install -r <requirements file according to table below>
+pip install -r requirements/full/<requirements file according to table below>
 ```
 
 Requirements file to use:
@@ -240,16 +240,16 @@ List of command-line flags
 
 ```txt
 usage: server.py [-h] [--multi-user] [--model MODEL] [--lora LORA [LORA ...]] [--model-dir MODEL_DIR] [--lora-dir LORA_DIR] [--model-menu] [--settings SETTINGS]
-                 [--extensions EXTENSIONS [EXTENSIONS ...]] [--verbose] [--idle-timeout IDLE_TIMEOUT] [--loader LOADER] [--cpu] [--cpu-memory CPU_MEMORY] [--disk] [--disk-cache-dir DISK_CACHE_DIR]
-                 [--load-in-8bit] [--bf16] [--no-cache] [--trust-remote-code] [--force-safetensors] [--no_use_fast] [--attn-implementation IMPLEMENTATION] [--load-in-4bit] [--use_double_quant]
-                 [--compute_dtype COMPUTE_DTYPE] [--quant_type QUANT_TYPE] [--flash-attn] [--threads THREADS] [--threads-batch THREADS_BATCH] [--batch-size BATCH_SIZE] [--no-mmap] [--mlock]
-                 [--gpu-layers N] [--tensor-split TENSOR_SPLIT] [--numa] [--no-kv-offload] [--row-split] [--extra-flags EXTRA_FLAGS] [--streaming-llm] [--mmproj MMPROJ] [--ctx-size N] [--cache-type N]
-                 [--model-draft MODEL_DRAFT] [--draft-max DRAFT_MAX] [--gpu-layers-draft GPU_LAYERS_DRAFT] [--device-draft DEVICE_DRAFT] [--ctx-size-draft CTX_SIZE_DRAFT] [--enable-tp]
-                 [--tp-backend TP_BACKEND] [--gpu-split GPU_SPLIT] [--autosplit] [--cfg-cache] [--no_flash_attn] [--no_xformers] [--no_sdpa] [--num_experts_per_token N] [--cpp-runner] [--deepspeed]
-                 [--nvme-offload-dir NVME_OFFLOAD_DIR] [--local_rank LOCAL_RANK] [--alpha_value ALPHA_VALUE] [--rope_freq_base ROPE_FREQ_BASE] [--compress_pos_emb COMPRESS_POS_EMB] [--listen]
-                 [--listen-port LISTEN_PORT] [--listen-host LISTEN_HOST] [--share] [--auto-launch] [--gradio-auth GRADIO_AUTH] [--gradio-auth-path GRADIO_AUTH_PATH] [--ssl-keyfile SSL_KEYFILE]
-                 [--ssl-certfile SSL_CERTFILE] [--subpath SUBPATH] [--old-colors] [--portable] [--api] [--public-api] [--public-api-id PUBLIC_API_ID] [--api-port API_PORT] [--api-key API_KEY]
-                 [--admin-key ADMIN_KEY] [--api-enable-ipv6] [--api-disable-ipv4] [--nowebui]
+                 [--extensions EXTENSIONS [EXTENSIONS ...]] [--verbose] [--idle-timeout IDLE_TIMEOUT] [--loader LOADER] [--ctx-size N] [--cache-type N] [--model-draft MODEL_DRAFT]
+                 [--draft-max DRAFT_MAX] [--gpu-layers-draft GPU_LAYERS_DRAFT] [--device-draft DEVICE_DRAFT] [--ctx-size-draft CTX_SIZE_DRAFT] [--gpu-layers N] [--mmproj MMPROJ] [--streaming-llm]
+                 [--tensor-split TENSOR_SPLIT] [--row-split] [--no-mmap] [--mlock] [--no-kv-offload] [--batch-size BATCH_SIZE] [--threads THREADS] [--threads-batch THREADS_BATCH] [--numa]
+                 [--extra-flags EXTRA_FLAGS] [--cpu] [--cpu-memory CPU_MEMORY] [--disk] [--disk-cache-dir DISK_CACHE_DIR] [--load-in-8bit] [--bf16] [--no-cache] [--trust-remote-code]
+                 [--force-safetensors] [--no_use_fast] [--attn-implementation IMPLEMENTATION] [--load-in-4bit] [--use_double_quant] [--compute_dtype COMPUTE_DTYPE] [--quant_type QUANT_TYPE]
+                 [--enable-tp] [--tp-backend TP_BACKEND] [--gpu-split GPU_SPLIT] [--autosplit] [--cfg-cache] [--no_flash_attn] [--no_xformers] [--no_sdpa] [--num_experts_per_token N] [--cpp-runner]
+                 [--deepspeed] [--nvme-offload-dir NVME_OFFLOAD_DIR] [--local_rank LOCAL_RANK] [--alpha_value ALPHA_VALUE] [--rope_freq_base ROPE_FREQ_BASE] [--compress_pos_emb COMPRESS_POS_EMB]
+                 [--listen] [--listen-port LISTEN_PORT] [--listen-host LISTEN_HOST] [--share] [--auto-launch] [--gradio-auth GRADIO_AUTH] [--gradio-auth-path GRADIO_AUTH_PATH]
+                 [--ssl-keyfile SSL_KEYFILE] [--ssl-certfile SSL_CERTFILE] [--subpath SUBPATH] [--old-colors] [--portable] [--api] [--public-api] [--public-api-id PUBLIC_API_ID] [--api-port API_PORT]
+                 [--api-key API_KEY] [--admin-key ADMIN_KEY] [--api-enable-ipv6] [--api-disable-ipv4] [--nowebui]
 
 Text Generation Web UI
 
@@ -273,6 +273,33 @@ Model loader:
   --loader LOADER                           Choose the model loader manually, otherwise, it will get autodetected. Valid options: Transformers, llama.cpp, ExLlamav3_HF, ExLlamav2_HF, ExLlamav2,
                                             TensorRT-LLM.
 
+Context and cache:
+  --ctx-size N, --n_ctx N, --max_seq_len N  Context size in tokens.
+  --cache-type N, --cache_type N            KV cache type; valid options: llama.cpp - fp16, q8_0, q4_0; ExLlamaV2 - fp16, fp8, q8, q6, q4; ExLlamaV3 - fp16, q2 to q8 (can specify k_bits and v_bits
+                                            separately, e.g. q4_q8).
+
+Speculative decoding:
+  --model-draft MODEL_DRAFT                 Path to the draft model for speculative decoding.
+  --draft-max DRAFT_MAX                     Number of tokens to draft for speculative decoding.
+  --gpu-layers-draft GPU_LAYERS_DRAFT       Number of layers to offload to the GPU for the draft model.
+  --device-draft DEVICE_DRAFT               Comma-separated list of devices to use for offloading the draft model. Example: CUDA0,CUDA1
+  --ctx-size-draft CTX_SIZE_DRAFT           Size of the prompt context for the draft model. If 0, uses the same as the main model.
+
+llama.cpp:
+  --gpu-layers N, --n-gpu-layers N          Number of layers to offload to the GPU.
+  --mmproj MMPROJ                           Path to the mmproj file for vision models.
+  --streaming-llm                           Activate StreamingLLM to avoid re-evaluating the entire prompt when old messages are removed.
+  --tensor-split TENSOR_SPLIT               Split the model across multiple GPUs. Comma-separated list of proportions. Example: 60,40.
+  --row-split                               Split the model by rows across GPUs. This may improve multi-gpu performance.
+  --no-mmap                                 Prevent mmap from being used.
+  --mlock                                   Force the system to keep the model in RAM.
+  --no-kv-offload                           Do not offload the K, Q, V to the GPU. This saves VRAM but reduces the performance.
+  --batch-size BATCH_SIZE                   Maximum number of prompt tokens to batch together when calling llama_eval.
+  --threads THREADS                         Number of threads to use.
+  --threads-batch THREADS_BATCH             Number of threads to use for batches/prompt processing.
+  --numa                                    Activate NUMA task allocation for llama.cpp.
+  --extra-flags EXTRA_FLAGS                 Extra flags to pass to llama-server. Format: "flag1=value1,flag2,flag3=value3". Example: "override-tensor=exps=CPU"
+
 Transformers/Accelerate:
   --cpu                                     Use the CPU to generate text. Warning: Training on CPU is extremely slow.
   --cpu-memory CPU_MEMORY                   Maximum CPU memory in GiB. Use this for CPU offloading.
@@ -292,34 +319,6 @@ bitsandbytes 4-bit:
   --compute_dtype COMPUTE_DTYPE             compute dtype for 4-bit. Valid options: bfloat16, float16, float32.
   --quant_type QUANT_TYPE                   quant_type for 4-bit. Valid options: nf4, fp4.
 
-llama.cpp:
-  --flash-attn                              Use flash-attention.
-  --threads THREADS                         Number of threads to use.
-  --threads-batch THREADS_BATCH             Number of threads to use for batches/prompt processing.
-  --batch-size BATCH_SIZE                   Maximum number of prompt tokens to batch together when calling llama_eval.
-  --no-mmap                                 Prevent mmap from being used.
-  --mlock                                   Force the system to keep the model in RAM.
-  --gpu-layers N, --n-gpu-layers N          Number of layers to offload to the GPU.
-  --tensor-split TENSOR_SPLIT               Split the model across multiple GPUs. Comma-separated list of proportions. Example: 60,40.
-  --numa                                    Activate NUMA task allocation for llama.cpp.
-  --no-kv-offload                           Do not offload the K, Q, V to the GPU. This saves VRAM but reduces the performance.
-  --row-split                               Split the model by rows across GPUs. This may improve multi-gpu performance.
-  --extra-flags EXTRA_FLAGS                 Extra flags to pass to llama-server. Format: "flag1=value1,flag2,flag3=value3". Example: "override-tensor=exps=CPU"
-  --streaming-llm                           Activate StreamingLLM to avoid re-evaluating the entire prompt when old messages are removed.
-  --mmproj MMPROJ                           Path to the mmproj file for vision models.
-
-Context and cache:
-  --ctx-size N, --n_ctx N, --max_seq_len N  Context size in tokens.
-  --cache-type N, --cache_type N            KV cache type; valid options: llama.cpp - fp16, q8_0, q4_0; ExLlamaV2 - fp16, fp8, q8, q6, q4; ExLlamaV3 - fp16, q2 to q8 (can specify k_bits and v_bits
-                                            separately, e.g. q4_q8).
-
-Speculative decoding:
-  --model-draft MODEL_DRAFT                 Path to the draft model for speculative decoding.
-  --draft-max DRAFT_MAX                     Number of tokens to draft for speculative decoding.
-  --gpu-layers-draft GPU_LAYERS_DRAFT       Number of layers to offload to the GPU for the draft model.
-  --device-draft DEVICE_DRAFT               Comma-separated list of devices to use for offloading the draft model. Example: CUDA0,CUDA1
-  --ctx-size-draft CTX_SIZE_DRAFT           Size of the prompt context for the draft model. If 0, uses the same as the main model.
-
 ExLlamaV3:
   --enable-tp, --enable_tp                  Enable Tensor Parallelism (TP) to split the model across GPUs.
   --tp-backend TP_BACKEND                   The backend for tensor parallelism. Valid options: native, nccl. Default: native.
diff --git a/css/main.css b/css/main.css
index c7ee57da..fd79d24c 100644
--- a/css/main.css
+++ b/css/main.css
@@ -22,10 +22,6 @@
     font-style: italic;
 }
 
-.tabs.svelte-710i53 {
-    margin-top: 0
-}
-
 .padded.svelte-12cmxck {
     padding: 3px 0;
 }
@@ -126,10 +122,6 @@ span.math.inline {
     vertical-align: baseline !important;
 }
 
-div.svelte-15lo0d8 > *, div.svelte-15lo0d8 > .form > * {
-    flex-wrap: nowrap;
-}
-
 gradio-app > :first-child {
     padding: 0 !important;
 }
@@ -325,7 +317,7 @@ audio {
 /* ----------------------------------------------
   Chat tab
 ---------------------------------------------- */
-.h-\[40dvh\], .wrap.svelte-byatnx.svelte-byatnx.svelte-byatnx {
+.h-\[40dvh\] {
     height: 66.67dvh
 }
 
@@ -338,23 +330,10 @@ audio {
     width: unset
 }
 
-div.svelte-362y77>*, div.svelte-362y77>.form>* {
-    flex-wrap: nowrap
-}
-
 .pending.svelte-1ed2p3z {
     opacity: 1;
 }
 
-.wrap.svelte-6roggh.svelte-6roggh {
-    max-height: 92.5%;
-}
-
-/* This is for the microphone button in the whisper extension */
-.sm.svelte-1ipelgc {
-    width: 100%;
-}
-
 #chat-tab {
     padding: 0;
 }
diff --git a/download-model.py b/download-model.py
index c0a3aa36..756d529f 100644
--- a/download-model.py
+++ b/download-model.py
@@ -242,9 +242,19 @@ class ModelDownloader:
                 try:
                     if output_path.exists() and not start_from_scratch:
                         current_file_size_on_disk = output_path.stat().st_size
-                        r_head = session.head(url, timeout=20)
-                        r_head.raise_for_status()
-                        total_size = int(r_head.headers.get('content-length', 0))
+
+                        # Make a HEAD request without following redirects to get metadata first
+                        r_head = session.head(url, timeout=20, allow_redirects=True)
+                        r_head.raise_for_status()  # Will raise an error for 4xx or 5xx status codes
+
+                        # Check for the new 'x-linked-size' header from Hugging Face
+                        if 'x-linked-size' in r_head.headers:
+                            total_size = int(r_head.headers['x-linked-size'])
+                        # Fallback to the old 'content-length' just in case
+                        elif 'content-length' in r_head.headers:
+                            total_size = int(r_head.headers.get('content-length', 0))
+                        else:
+                            total_size = 0
 
                         if current_file_size_on_disk >= total_size and total_size > 0:
                             if self.progress_queue is not None and total_size > 0:
diff --git a/modules/chat.py b/modules/chat.py
index 9857479a..55984d7a 100644
--- a/modules/chat.py
+++ b/modules/chat.py
@@ -880,7 +880,9 @@ def chatbot_wrapper(text, state, regenerate=False, _continue=False, loading_mess
 
         # Extract the reply
         if state['mode'] in ['chat', 'chat-instruct']:
-            reply = reply.lstrip()
+            if not _continue:
+                reply = reply.lstrip()
+
             if reply.startswith(state['name2'] + ':'):
                 reply = reply[len(state['name2'] + ':'):]
             elif reply.startswith(state['name1'] + ':'):
@@ -1831,6 +1833,10 @@ def handle_branch_chat_click(state):
         history = state['history']
         history['visible'] = history['visible'][:branch_from_index + 1]
         history['internal'] = history['internal'][:branch_from_index + 1]
+        # Prune the metadata dictionary to remove entries beyond the branch point
+        if 'metadata' in history:
+            history['metadata'] = {k: v for k, v in history['metadata'].items() if int(k.split('_')[-1]) <= branch_from_index}
+
     new_unique_id = datetime.now().strftime('%Y%m%d-%H-%M-%S')
     save_history(history, new_unique_id, state['character_menu'], state['mode'])
 
diff --git a/modules/exllamav3_hf.py b/modules/exllamav3_hf.py
index c606912b..e05f8d7d 100644
--- a/modules/exllamav3_hf.py
+++ b/modules/exllamav3_hf.py
@@ -4,8 +4,6 @@ from pathlib import Path
 from typing import Any, Dict, Optional, Union
 
 import torch
-from exllamav3 import Cache, Config, Model
-from exllamav3.cache import CacheLayer_fp16, CacheLayer_quant
 from torch.nn import CrossEntropyLoss
 from transformers import (
     GenerationConfig,
@@ -15,6 +13,8 @@ from transformers import (
 )
 from transformers.modeling_outputs import CausalLMOutputWithPast
 
+from exllamav3 import Cache, Config, Model
+from exllamav3.cache import CacheLayer_fp16, CacheLayer_quant
 from modules import shared
 from modules.logging_colors import logger
 
@@ -103,12 +103,6 @@ class Exllamav3HF(PreTrainedModel, GenerationMixin):
         labels = kwargs.get('labels', None)
         past_key_values = kwargs.get('past_key_values', None)
 
-        # Reset the internal sequence state for standalone calls (logit viewer)
-        # or the very first step of a new generation.
-        if past_key_values is None:
-            self.past_seq = None
-            self.past_seq_negative = None
-
         if len(args) > 0:
             if not shared.args.cfg_cache:
                 logger.error("Please enable the cfg-cache option to use CFG with ExLlamav3_HF.")
@@ -125,8 +119,8 @@ class Exllamav3HF(PreTrainedModel, GenerationMixin):
             ex_cache = self.ex_cache
 
         seq = input_ids[0].tolist()
-        if is_negative and past_key_values is not None and isinstance(past_key_values, list):
-             seq = past_key_values + seq
+        if is_negative and past_key_values is not None:
+            seq = past_key_values + seq
 
         seq_tensor = torch.tensor(seq)
         reset = True
@@ -134,50 +128,97 @@ class Exllamav3HF(PreTrainedModel, GenerationMixin):
         # Maximum number of tokens to process in a single forward pass
         max_chunk_size = 256
 
-        if past_seq is not None:
-            min_length = min(past_seq.shape[0], seq_tensor.shape[0])
-            indices = torch.nonzero(~torch.eq(past_seq[:min_length], seq_tensor[:min_length]))
-            if len(indices) == 0 and seq_tensor.shape[0] > past_seq.shape[0]:
-                reset = False
-
-        # Create a single `params` dictionary that will be used and modified
-        # in-place across all `forward` calls within this function.
-        params = {
-            "attn_mode": "flash_attn",
-            "cache": ex_cache,
-            "batch_shape": (1, self.max_tokens),
-            "reconstruct": False,
-            "past_len": 0
-        }
-
         # Make the forward call
         if labels is None:
-            # If it's an efficient continuation, process only the new tokens
-            if not reset:
-                params["past_len"] = past_seq.shape[0]
-                tokens_to_process = seq_tensor[past_seq.shape[0]:]
-            # Otherwise, process the whole sequence from scratch
-            else:
-                tokens_to_process = seq_tensor
+            if past_seq is not None:
+                min_length = min(past_seq.shape[0], seq_tensor.shape[0])
+                indices = torch.nonzero(~torch.eq(past_seq[:min_length], seq_tensor[:min_length]))
+                if len(indices) > 0:
+                    longest_prefix = indices[0].item()
+                else:
+                    longest_prefix = min_length
 
-            # Process all but the last token of the sequence/sub-sequence
-            if tokens_to_process.shape[0] > 1:
-                prefix_to_process = tokens_to_process[:-1]
+                if longest_prefix > 0:
+                    reset = False
+                    current_len = longest_prefix
+                    remaining_tokens = len(seq_tensor) - longest_prefix - 1
 
-                # Process in chunks if the number of tokens is large
-                for i in range(0, prefix_to_process.shape[0], max_chunk_size):
-                    chunk = prefix_to_process[i:i + max_chunk_size]
-                    self.ex_model.forward(input_ids=chunk.view(1, -1), params=params)
-                    params["past_len"] += chunk.shape[0]
+                    if remaining_tokens > 0:
+                        # Process tokens from longest_prefix to second-to-last token
+                        tokens_to_process = seq_tensor[longest_prefix:-1]
 
-            # Process the last token to get logits
-            last_token = tokens_to_process[-1:].view(1, -1)
-            logits = self.ex_model.forward(input_ids=last_token, params=params).to(input_ids.device).float()
+                        # Process in chunks if the number of tokens is large
+                        for i in range(0, tokens_to_process.shape[0], max_chunk_size):
+                            chunk = tokens_to_process[i:i + max_chunk_size]
+                            self.ex_model.forward(
+                                input_ids=chunk.view(1, -1),
+                                params={
+                                    "attn_mode": "flash_attn",
+                                    "cache": ex_cache,
+                                    "past_len": longest_prefix + i,
+                                    "batch_shape": (1, self.max_tokens),
+                                    "reconstruct": False  # Force memory-efficient path
+                                }
+                            )
+
+                        current_len = longest_prefix + remaining_tokens
+
+            if reset:
+                if len(seq_tensor) > 1:
+                    # Process all tokens except the last one
+                    tokens_to_process = seq_tensor[:-1]
+
+                    # Process in chunks if the number of tokens is large
+                    current_len = 0
+                    for i in range(0, tokens_to_process.shape[0], max_chunk_size):
+                        chunk = tokens_to_process[i:i + max_chunk_size]
+                        self.ex_model.forward(
+                            input_ids=chunk.view(1, -1),
+                            params={
+                                "attn_mode": "flash_attn",
+                                "cache": ex_cache,
+                                "past_len": current_len,
+                                "batch_shape": (1, self.max_tokens),
+                                "reconstruct": False  # Force memory-efficient path
+                            }
+                        )
+                        current_len += chunk.shape[0]
+                else:
+                    current_len = 0
+
+            # Process the last token and get logits
+            logits = self.ex_model.forward(
+                input_ids=seq_tensor[-1:].view(1, -1),
+                params={
+                    "attn_mode": "flash_attn",
+                    "cache": ex_cache,
+                    "past_len": current_len,
+                    "batch_shape": (1, self.max_tokens),
+                    "reconstruct": False  # Force memory-efficient path
+                }
+            ).to(input_ids.device).float()
         else:
             # When processing with labels, handle as a complete sequence
-            params["attn_mode"] = "flash_attn_nc"
-            logits = self.ex_model.forward(input_ids=seq_tensor.view(1,-1), params=params).float()
+            # Process in chunks if the number of tokens is large
+            tokens_to_process = seq_tensor
+            all_logits = None
 
+            for i in range(0, tokens_to_process.shape[0], max_chunk_size):
+                chunk = tokens_to_process[i:i + max_chunk_size]
+                chunk_logits = self.ex_model.forward(
+                    input_ids=chunk.view(1, -1),
+                    params={
+                        "attn_mode": "flash_attn_nc",  # No caching for training
+                        "reconstruct": False  # Force memory-efficient path
+                    }
+                ).float()
+
+                if all_logits is None:
+                    all_logits = chunk_logits
+                else:
+                    all_logits = torch.cat([all_logits, chunk_logits], dim=1)
+
+            logits = all_logits
 
         if is_negative:
             self.past_seq_negative = seq_tensor
diff --git a/modules/llama_cpp_server.py b/modules/llama_cpp_server.py
index 38589cf2..27890d8c 100644
--- a/modules/llama_cpp_server.py
+++ b/modules/llama_cpp_server.py
@@ -200,7 +200,10 @@ class LlamaServer:
         # Make the generation request
         response = self.session.post(url, json=payload, stream=True)
         try:
-            response.raise_for_status()  # Raise an exception for HTTP errors
+            if response.status_code == 400 and response.json()["error"]["type"] == "exceed_context_size_error":
+                logger.error("The request exceeds the available context size, try increasing it")
+            else:
+                response.raise_for_status()  # Raise an exception for HTTP errors
 
             full_text = ""
 
diff --git a/modules/loaders.py b/modules/loaders.py
index fe982ab5..609a54c6 100644
--- a/modules/loaders.py
+++ b/modules/loaders.py
@@ -45,7 +45,6 @@ loaders_and_params = OrderedDict({
         'disk',
         'use_double_quant',
         'bf16',
-        'trust_remote_code',
         'no_use_fast',
     ],
     'ExLlamav3_HF': [
@@ -53,7 +52,6 @@ loaders_and_params = OrderedDict({
         'cache_type',
         'gpu_split',
         'cfg_cache',
-        'trust_remote_code',
         'no_use_fast',
         'enable_tp',
         'tp_backend',
@@ -82,7 +80,6 @@ loaders_and_params = OrderedDict({
         'no_xformers',
         'no_sdpa',
         'cfg_cache',
-        'trust_remote_code',
         'no_use_fast',
     ],
     'ExLlamav2': [
diff --git a/modules/shared.py b/modules/shared.py
index 4daf43c9..e54ba654 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -50,6 +50,35 @@ group.add_argument('--idle-timeout', type=int, default=0, help='Unload model aft
 group = parser.add_argument_group('Model loader')
 group.add_argument('--loader', type=str, help='Choose the model loader manually, otherwise, it will get autodetected. Valid options: Transformers, llama.cpp, ExLlamav3_HF, ExLlamav2_HF, ExLlamav2, TensorRT-LLM.')
 
+# Cache
+group = parser.add_argument_group('Context and cache')
+group.add_argument('--ctx-size', '--n_ctx', '--max_seq_len', type=int, default=8192, metavar='N', help='Context size in tokens.')
+group.add_argument('--cache-type', '--cache_type', type=str, default='fp16', metavar='N', help='KV cache type; valid options: llama.cpp - fp16, q8_0, q4_0; ExLlamaV2 - fp16, fp8, q8, q6, q4; ExLlamaV3 - fp16, q2 to q8 (can specify k_bits and v_bits separately, e.g. q4_q8).')
+
+# Speculative decoding
+group = parser.add_argument_group('Speculative decoding')
+group.add_argument('--model-draft', type=str, default=None, help='Path to the draft model for speculative decoding.')
+group.add_argument('--draft-max', type=int, default=4, help='Number of tokens to draft for speculative decoding.')
+group.add_argument('--gpu-layers-draft', type=int, default=256, help='Number of layers to offload to the GPU for the draft model.')
+group.add_argument('--device-draft', type=str, default=None, help='Comma-separated list of devices to use for offloading the draft model. Example: CUDA0,CUDA1')
+group.add_argument('--ctx-size-draft', type=int, default=0, help='Size of the prompt context for the draft model. If 0, uses the same as the main model.')
+
+# llama.cpp
+group = parser.add_argument_group('llama.cpp')
+group.add_argument('--gpu-layers', '--n-gpu-layers', type=int, default=256, metavar='N', help='Number of layers to offload to the GPU.')
+group.add_argument('--mmproj', type=str, default=None, help='Path to the mmproj file for vision models.')
+group.add_argument('--streaming-llm', action='store_true', help='Activate StreamingLLM to avoid re-evaluating the entire prompt when old messages are removed.')
+group.add_argument('--tensor-split', type=str, default=None, help='Split the model across multiple GPUs. Comma-separated list of proportions. Example: 60,40.')
+group.add_argument('--row-split', action='store_true', help='Split the model by rows across GPUs. This may improve multi-gpu performance.')
+group.add_argument('--no-mmap', action='store_true', help='Prevent mmap from being used.')
+group.add_argument('--mlock', action='store_true', help='Force the system to keep the model in RAM.')
+group.add_argument('--no-kv-offload', action='store_true', help='Do not offload the  K, Q, V to the GPU. This saves VRAM but reduces the performance.')
+group.add_argument('--batch-size', type=int, default=256, help='Maximum number of prompt tokens to batch together when calling llama_eval.')
+group.add_argument('--threads', type=int, default=0, help='Number of threads to use.')
+group.add_argument('--threads-batch', type=int, default=0, help='Number of threads to use for batches/prompt processing.')
+group.add_argument('--numa', action='store_true', help='Activate NUMA task allocation for llama.cpp.')
+group.add_argument('--extra-flags', type=str, default=None, help='Extra flags to pass to llama-server. Format: "flag1=value1,flag2,flag3=value3". Example: "override-tensor=exps=CPU"')
+
 # Transformers/Accelerate
 group = parser.add_argument_group('Transformers/Accelerate')
 group.add_argument('--cpu', action='store_true', help='Use the CPU to generate text. Warning: Training on CPU is extremely slow.')
@@ -71,35 +100,6 @@ group.add_argument('--use_double_quant', action='store_true', help='use_double_q
 group.add_argument('--compute_dtype', type=str, default='float16', help='compute dtype for 4-bit. Valid options: bfloat16, float16, float32.')
 group.add_argument('--quant_type', type=str, default='nf4', help='quant_type for 4-bit. Valid options: nf4, fp4.')
 
-# llama.cpp
-group = parser.add_argument_group('llama.cpp')
-group.add_argument('--threads', type=int, default=0, help='Number of threads to use.')
-group.add_argument('--threads-batch', type=int, default=0, help='Number of threads to use for batches/prompt processing.')
-group.add_argument('--batch-size', type=int, default=256, help='Maximum number of prompt tokens to batch together when calling llama_eval.')
-group.add_argument('--no-mmap', action='store_true', help='Prevent mmap from being used.')
-group.add_argument('--mlock', action='store_true', help='Force the system to keep the model in RAM.')
-group.add_argument('--gpu-layers', '--n-gpu-layers', type=int, default=256, metavar='N', help='Number of layers to offload to the GPU.')
-group.add_argument('--tensor-split', type=str, default=None, help='Split the model across multiple GPUs. Comma-separated list of proportions. Example: 60,40.')
-group.add_argument('--numa', action='store_true', help='Activate NUMA task allocation for llama.cpp.')
-group.add_argument('--no-kv-offload', action='store_true', help='Do not offload the  K, Q, V to the GPU. This saves VRAM but reduces the performance.')
-group.add_argument('--row-split', action='store_true', help='Split the model by rows across GPUs. This may improve multi-gpu performance.')
-group.add_argument('--extra-flags', type=str, default=None, help='Extra flags to pass to llama-server. Format: "flag1=value1,flag2,flag3=value3". Example: "override-tensor=exps=CPU"')
-group.add_argument('--streaming-llm', action='store_true', help='Activate StreamingLLM to avoid re-evaluating the entire prompt when old messages are removed.')
-group.add_argument('--mmproj', type=str, default=None, help='Path to the mmproj file for vision models.')
-
-# Cache
-group = parser.add_argument_group('Context and cache')
-group.add_argument('--ctx-size', '--n_ctx', '--max_seq_len', type=int, default=8192, metavar='N', help='Context size in tokens.')
-group.add_argument('--cache-type', '--cache_type', type=str, default='fp16', metavar='N', help='KV cache type; valid options: llama.cpp - fp16, q8_0, q4_0; ExLlamaV2 - fp16, fp8, q8, q6, q4; ExLlamaV3 - fp16, q2 to q8 (can specify k_bits and v_bits separately, e.g. q4_q8).')
-
-# Speculative decoding
-group = parser.add_argument_group('Speculative decoding')
-group.add_argument('--model-draft', type=str, default=None, help='Path to the draft model for speculative decoding.')
-group.add_argument('--draft-max', type=int, default=4, help='Number of tokens to draft for speculative decoding.')
-group.add_argument('--gpu-layers-draft', type=int, default=256, help='Number of layers to offload to the GPU for the draft model.')
-group.add_argument('--device-draft', type=str, default=None, help='Comma-separated list of devices to use for offloading the draft model. Example: CUDA0,CUDA1')
-group.add_argument('--ctx-size-draft', type=int, default=0, help='Size of the prompt context for the draft model. If 0, uses the same as the main model.')
-
 # ExLlamaV3
 group = parser.add_argument_group('ExLlamaV3')
 group.add_argument('--enable-tp', '--enable_tp', action='store_true', help='Enable Tensor Parallelism (TP) to split the model across GPUs.')
@@ -174,6 +174,7 @@ if cmd_flags_path.exists():
 
 
 args = parser.parse_args()
+original_args = copy.deepcopy(args)
 args_defaults = parser.parse_args([])
 
 # Create a mapping of all argument aliases to their canonical names
@@ -295,7 +296,13 @@ default_settings = copy.deepcopy(settings)
 def do_cmd_flags_warnings():
     # Security warnings
     if args.trust_remote_code:
-        logger.warning('trust_remote_code is enabled. This is dangerous.')
+        logger.warning(
+            "The `--trust-remote-code` flag is enabled.\n"
+            "This allows models to execute arbitrary code on your machine.\n\n"
+            "1. Only use with models from sources you fully trust.\n"
+            "2. Set an access password with `--gradio-auth`."
+        )
+
     if 'COLAB_GPU' not in os.environ and not args.nowebui:
         if args.share:
             logger.warning("The gradio \"share link\" feature uses a proprietary executable to create a reverse tunnel. Use it with care.")
diff --git a/modules/transformers_loader.py b/modules/transformers_loader.py
index 7866f448..f1af1299 100644
--- a/modules/transformers_loader.py
+++ b/modules/transformers_loader.py
@@ -123,7 +123,7 @@ def load_tokenizer(model_name, tokenizer_dir=None):
 
         tokenizer = AutoTokenizer.from_pretrained(
             path_to_model,
-            trust_remote_code=shared.args.trust_remote_code,
+            trust_remote_code=shared.original_args.trust_remote_code,
             use_fast=not shared.args.no_use_fast
         )
 
@@ -140,13 +140,13 @@ def load_model_HF(model_name):
         'torch_dtype': torch.bfloat16 if shared.args.bf16 else torch.float16,
     }
 
-    if shared.args.trust_remote_code:
+    if shared.original_args.trust_remote_code:
         params['trust_remote_code'] = True
 
     if shared.args.force_safetensors:
         params['force_safetensors'] = True
 
-    config = AutoConfig.from_pretrained(path_to_model, trust_remote_code=shared.args.trust_remote_code)
+    config = AutoConfig.from_pretrained(path_to_model, trust_remote_code=shared.original_args.trust_remote_code)
 
     if 'chatglm' in model_name.lower():
         LoaderClass = AutoModel
diff --git a/modules/ui.py b/modules/ui.py
index 12f43768..76533767 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -160,7 +160,6 @@ def list_model_elements():
         'no_sdpa',
         'cfg_cache',
         'cpp_runner',
-        'trust_remote_code',
         'no_use_fast',
         'model_draft',
         'draft_max',
diff --git a/modules/ui_model_menu.py b/modules/ui_model_menu.py
index 729700d4..50ada9f9 100644
--- a/modules/ui_model_menu.py
+++ b/modules/ui_model_menu.py
@@ -57,7 +57,6 @@ def create_ui():
                             shared.gradio['autosplit'] = gr.Checkbox(label="autosplit", value=shared.args.autosplit, info='Automatically split the model tensors across the available GPUs.')
                             shared.gradio['enable_tp'] = gr.Checkbox(label="enable_tp", value=shared.args.enable_tp, info='Enable tensor parallelism (TP).')
                             shared.gradio['cpp_runner'] = gr.Checkbox(label="cpp-runner", value=shared.args.cpp_runner, info='Enable inference with ModelRunnerCpp, which is faster than the default ModelRunner.')
-                            shared.gradio['trust_remote_code'] = gr.Checkbox(label="trust-remote-code", value=shared.args.trust_remote_code, info='Set trust_remote_code=True while loading the tokenizer/model. To enable this option, start the web UI with the --trust-remote-code flag.', interactive=shared.args.trust_remote_code)
                             shared.gradio['tensorrt_llm_info'] = gr.Markdown('* TensorRT-LLM has to be installed manually in a separate Python 3.10 environment at the moment. For a guide, consult the description of [this PR](https://github.com/oobabooga/text-generation-webui/pull/5715). \n\n* `ctx_size` is only used when `cpp-runner` is checked.\n\n* `cpp_runner` does not support streaming at the moment.')
 
                             # Multimodal
diff --git a/requirements/full/requirements.txt b/requirements/full/requirements.txt
index 97eac769..0609f69b 100644
--- a/requirements/full/requirements.txt
+++ b/requirements/full/requirements.txt
@@ -6,7 +6,6 @@ datasets
 einops
 fastapi==0.112.4
 flash-linear-attention==0.3.2
-gradio==4.37.*
 html2text==2025.4.15
 jinja2==3.1.6
 markdown
@@ -15,7 +14,7 @@ pandas
 peft==0.17.*
 Pillow>=9.5.0
 psutil
-pydantic==2.8.2
+pydantic==2.11.0
 PyPDF2==3.0.1
 python-docx==1.1.2
 pyyaml
@@ -30,16 +29,20 @@ triton-windows==3.3.1.post19; platform_system == "Windows"
 tqdm
 wandb
 
+# Gradio
+gradio==4.37.*
+https://github.com/oobabooga/gradio/releases/download/custom-build/gradio_client-1.0.2+custom.1-py3-none-any.whl
+
 # API
 flask_cloudflared==0.0.14
 sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0+cu124-py3-none-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/v0.0.7/exllamav3-0.0.7+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/v0.0.7/exllamav3-0.0.7+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/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+cu124-py3-none-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/v0.0.10/exllamav3-0.0.10+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/v0.0.10/exllamav3-0.0.10+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_amd.txt b/requirements/full/requirements_amd.txt
index b3b0005e..73d35185 100644
--- a/requirements/full/requirements_amd.txt
+++ b/requirements/full/requirements_amd.txt
@@ -4,7 +4,6 @@ colorama
 datasets
 einops
 fastapi==0.112.4
-gradio==4.37.*
 html2text==2025.4.15
 jinja2==3.1.6
 markdown
@@ -13,7 +12,7 @@ pandas
 peft==0.17.*
 Pillow>=9.5.0
 psutil
-pydantic==2.8.2
+pydantic==2.11.0
 PyPDF2==3.0.1
 python-docx==1.1.2
 pyyaml
@@ -28,13 +27,17 @@ triton-windows==3.2.0.post19; platform_system == "Windows"
 tqdm
 wandb
 
+# Gradio
+gradio==4.37.*
+https://github.com/oobabooga/gradio/releases/download/custom-build/gradio_client-1.0.2+custom.1-py3-none-any.whl
+
 # API
 flask_cloudflared==0.0.14
 sse-starlette==1.6.5
 tiktoken
 
 # AMD wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+vulkan-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 5e0d375e..dad354e6 100644
--- a/requirements/full/requirements_amd_noavx2.txt
+++ b/requirements/full/requirements_amd_noavx2.txt
@@ -4,7 +4,6 @@ colorama
 datasets
 einops
 fastapi==0.112.4
-gradio==4.37.*
 html2text==2025.4.15
 jinja2==3.1.6
 markdown
@@ -13,7 +12,7 @@ pandas
 peft==0.17.*
 Pillow>=9.5.0
 psutil
-pydantic==2.8.2
+pydantic==2.11.0
 PyPDF2==3.0.1
 python-docx==1.1.2
 pyyaml
@@ -28,13 +27,17 @@ triton-windows==3.2.0.post19; platform_system == "Windows"
 tqdm
 wandb
 
+# Gradio
+gradio==4.37.*
+https://github.com/oobabooga/gradio/releases/download/custom-build/gradio_client-1.0.2+custom.1-py3-none-any.whl
+
 # API
 flask_cloudflared==0.0.14
 sse-starlette==1.6.5
 tiktoken
 
 # AMD wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+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 0bb837ba..ab48c839 100644
--- a/requirements/full/requirements_apple_intel.txt
+++ b/requirements/full/requirements_apple_intel.txt
@@ -4,7 +4,6 @@ colorama
 datasets
 einops
 fastapi==0.112.4
-gradio==4.37.*
 html2text==2025.4.15
 jinja2==3.1.6
 markdown
@@ -13,7 +12,7 @@ pandas
 peft==0.17.*
 Pillow>=9.5.0
 psutil
-pydantic==2.8.2
+pydantic==2.11.0
 PyPDF2==3.0.1
 python-docx==1.1.2
 pyyaml
@@ -28,11 +27,15 @@ triton-windows==3.2.0.post19; platform_system == "Windows"
 tqdm
 wandb
 
+# Gradio
+gradio==4.37.*
+https://github.com/oobabooga/gradio/releases/download/custom-build/gradio_client-1.0.2+custom.1-py3-none-any.whl
+
 # API
 flask_cloudflared==0.0.14
 sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and platform_release < "25.0.0" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and platform_release < "25.0.0" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11"
diff --git a/requirements/full/requirements_apple_silicon.txt b/requirements/full/requirements_apple_silicon.txt
index 514c0662..3a341b8a 100644
--- a/requirements/full/requirements_apple_silicon.txt
+++ b/requirements/full/requirements_apple_silicon.txt
@@ -4,7 +4,6 @@ colorama
 datasets
 einops
 fastapi==0.112.4
-gradio==4.37.*
 html2text==2025.4.15
 jinja2==3.1.6
 markdown
@@ -13,7 +12,7 @@ pandas
 peft==0.17.*
 Pillow>=9.5.0
 psutil
-pydantic==2.8.2
+pydantic==2.11.0
 PyPDF2==3.0.1
 python-docx==1.1.2
 pyyaml
@@ -28,12 +27,16 @@ triton-windows==3.2.0.post19; platform_system == "Windows"
 tqdm
 wandb
 
+# Gradio
+gradio==4.37.*
+https://github.com/oobabooga/gradio/releases/download/custom-build/gradio_client-1.0.2+custom.1-py3-none-any.whl
+
 # API
 flask_cloudflared==0.0.14
 sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and platform_release < "25.0.0" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0-py3-none-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0-py3-none-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and platform_release < "25.0.0" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0-py3-none-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0-py3-none-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.11"
diff --git a/requirements/full/requirements_cpu_only.txt b/requirements/full/requirements_cpu_only.txt
index f68fdd9d..3765d329 100644
--- a/requirements/full/requirements_cpu_only.txt
+++ b/requirements/full/requirements_cpu_only.txt
@@ -4,7 +4,6 @@ colorama
 datasets
 einops
 fastapi==0.112.4
-gradio==4.37.*
 html2text==2025.4.15
 jinja2==3.1.6
 markdown
@@ -13,7 +12,7 @@ pandas
 peft==0.17.*
 Pillow>=9.5.0
 psutil
-pydantic==2.8.2
+pydantic==2.11.0
 PyPDF2==3.0.1
 python-docx==1.1.2
 pyyaml
@@ -28,11 +27,15 @@ triton-windows==3.2.0.post19; platform_system == "Windows"
 tqdm
 wandb
 
+# Gradio
+gradio==4.37.*
+https://github.com/oobabooga/gradio/releases/download/custom-build/gradio_client-1.0.2+custom.1-py3-none-any.whl
+
 # API
 flask_cloudflared==0.0.14
 sse-starlette==1.6.5
 tiktoken
 
 # llama.cpp (CPU only, AVX2)
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
diff --git a/requirements/full/requirements_cpu_only_noavx2.txt b/requirements/full/requirements_cpu_only_noavx2.txt
index b40f1af2..a3e4e516 100644
--- a/requirements/full/requirements_cpu_only_noavx2.txt
+++ b/requirements/full/requirements_cpu_only_noavx2.txt
@@ -4,7 +4,6 @@ colorama
 datasets
 einops
 fastapi==0.112.4
-gradio==4.37.*
 html2text==2025.4.15
 jinja2==3.1.6
 markdown
@@ -13,7 +12,7 @@ pandas
 peft==0.17.*
 Pillow>=9.5.0
 psutil
-pydantic==2.8.2
+pydantic==2.11.0
 PyPDF2==3.0.1
 python-docx==1.1.2
 pyyaml
@@ -28,11 +27,15 @@ triton-windows==3.2.0.post19; platform_system == "Windows"
 tqdm
 wandb
 
+# Gradio
+gradio==4.37.*
+https://github.com/oobabooga/gradio/releases/download/custom-build/gradio_client-1.0.2+custom.1-py3-none-any.whl
+
 # API
 flask_cloudflared==0.0.14
 sse-starlette==1.6.5
 tiktoken
 
 # llama.cpp (CPU only, no AVX2)
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
diff --git a/requirements/full/requirements_noavx2.txt b/requirements/full/requirements_noavx2.txt
index 9de9e65a..abdd262e 100644
--- a/requirements/full/requirements_noavx2.txt
+++ b/requirements/full/requirements_noavx2.txt
@@ -6,7 +6,6 @@ datasets
 einops
 fastapi==0.112.4
 flash-linear-attention==0.3.2
-gradio==4.37.*
 html2text==2025.4.15
 jinja2==3.1.6
 markdown
@@ -15,7 +14,7 @@ pandas
 peft==0.17.*
 Pillow>=9.5.0
 psutil
-pydantic==2.8.2
+pydantic==2.11.0
 PyPDF2==3.0.1
 python-docx==1.1.2
 pyyaml
@@ -30,16 +29,20 @@ triton-windows==3.3.1.post19; platform_system == "Windows"
 tqdm
 wandb
 
+# Gradio
+gradio==4.37.*
+https://github.com/oobabooga/gradio/releases/download/custom-build/gradio_client-1.0.2+custom.1-py3-none-any.whl
+
 # API
 flask_cloudflared==0.0.14
 sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0+cu124avx-py3-none-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/v0.0.7/exllamav3-0.0.7+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/v0.0.7/exllamav3-0.0.7+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/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+cu124avx-py3-none-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/v0.0.10/exllamav3-0.0.10+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/v0.0.10/exllamav3-0.0.10+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_nowheels.txt b/requirements/full/requirements_nowheels.txt
index 3bd20dd9..47b0dcbd 100644
--- a/requirements/full/requirements_nowheels.txt
+++ b/requirements/full/requirements_nowheels.txt
@@ -4,7 +4,6 @@ colorama
 datasets
 einops
 fastapi==0.112.4
-gradio==4.37.*
 html2text==2025.4.15
 jinja2==3.1.6
 markdown
@@ -13,7 +12,7 @@ pandas
 peft==0.17.*
 Pillow>=9.5.0
 psutil
-pydantic==2.8.2
+pydantic==2.11.0
 PyPDF2==3.0.1
 python-docx==1.1.2
 pyyaml
@@ -28,6 +27,10 @@ triton-windows==3.2.0.post19; platform_system == "Windows"
 tqdm
 wandb
 
+# Gradio
+gradio==4.37.*
+https://github.com/oobabooga/gradio/releases/download/custom-build/gradio_client-1.0.2+custom.1-py3-none-any.whl
+
 # API
 flask_cloudflared==0.0.14
 sse-starlette==1.6.5
diff --git a/requirements/portable/requirements.txt b/requirements/portable/requirements.txt
index 7a38b1e6..d43007d0 100644
--- a/requirements/portable/requirements.txt
+++ b/requirements/portable/requirements.txt
@@ -1,11 +1,10 @@
 audioop-lts<1.0; python_version >= "3.13"
 fastapi==0.112.4
-gradio==4.37.*
 html2text==2025.4.15
 jinja2==3.1.6
 markdown
 numpy==2.2.*
-pydantic==2.8.2
+pydantic==2.11.0
 PyPDF2==3.0.1
 python-docx==1.1.2
 pyyaml
@@ -13,11 +12,15 @@ requests
 rich
 tqdm
 
+# Gradio
+gradio==4.37.*
+https://github.com/oobabooga/gradio/releases/download/custom-build/gradio_client-1.0.2+custom.1-py3-none-any.whl
+
 # API
 flask_cloudflared==0.0.14
 sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+cu124-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 047d1c54..77a66dd8 100644
--- a/requirements/portable/requirements_apple_intel.txt
+++ b/requirements/portable/requirements_apple_intel.txt
@@ -1,11 +1,10 @@
 audioop-lts<1.0; python_version >= "3.13"
 fastapi==0.112.4
-gradio==4.37.*
 html2text==2025.4.15
 jinja2==3.1.6
 markdown
 numpy==2.2.*
-pydantic==2.8.2
+pydantic==2.11.0
 PyPDF2==3.0.1
 python-docx==1.1.2
 pyyaml
@@ -13,12 +12,16 @@ requests
 rich
 tqdm
 
+# Gradio
+gradio==4.37.*
+https://github.com/oobabooga/gradio/releases/download/custom-build/gradio_client-1.0.2+custom.1-py3-none-any.whl
+
 # API
 flask_cloudflared==0.0.14
 sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and platform_release < "25.0.0"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0-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/v0.49.0/llama_cpp_binaries-0.49.0-py3-none-macosx_13_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0"
\ No newline at end of file
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and platform_release < "25.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0-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/v0.53.0/llama_cpp_binaries-0.53.0-py3-none-macosx_13_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0"
diff --git a/requirements/portable/requirements_apple_silicon.txt b/requirements/portable/requirements_apple_silicon.txt
index 5c8ae4df..a2479e98 100644
--- a/requirements/portable/requirements_apple_silicon.txt
+++ b/requirements/portable/requirements_apple_silicon.txt
@@ -1,11 +1,10 @@
 audioop-lts<1.0; python_version >= "3.13"
 fastapi==0.112.4
-gradio==4.37.*
 html2text==2025.4.15
 jinja2==3.1.6
 markdown
 numpy==2.2.*
-pydantic==2.8.2
+pydantic==2.11.0
 PyPDF2==3.0.1
 python-docx==1.1.2
 pyyaml
@@ -13,12 +12,16 @@ requests
 rich
 tqdm
 
+# Gradio
+gradio==4.37.*
+https://github.com/oobabooga/gradio/releases/download/custom-build/gradio_client-1.0.2+custom.1-py3-none-any.whl
+
 # API
 flask_cloudflared==0.0.14
 sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and platform_release < "25.0.0"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0-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/v0.49.0/llama_cpp_binaries-0.49.0-py3-none-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and platform_release < "25.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0-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/v0.53.0/llama_cpp_binaries-0.53.0-py3-none-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0"
diff --git a/requirements/portable/requirements_cpu_only.txt b/requirements/portable/requirements_cpu_only.txt
index f41efd58..8d8e5233 100644
--- a/requirements/portable/requirements_cpu_only.txt
+++ b/requirements/portable/requirements_cpu_only.txt
@@ -1,11 +1,10 @@
 audioop-lts<1.0; python_version >= "3.13"
 fastapi==0.112.4
-gradio==4.37.*
 html2text==2025.4.15
 jinja2==3.1.6
 markdown
 numpy==2.2.*
-pydantic==2.8.2
+pydantic==2.11.0
 PyPDF2==3.0.1
 python-docx==1.1.2
 pyyaml
@@ -13,11 +12,15 @@ requests
 rich
 tqdm
 
+# Gradio
+gradio==4.37.*
+https://github.com/oobabooga/gradio/releases/download/custom-build/gradio_client-1.0.2+custom.1-py3-none-any.whl
+
 # API
 flask_cloudflared==0.0.14
 sse-starlette==1.6.5
 tiktoken
 
 # llama.cpp (CPU only, AVX2)
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+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 69158050..08b7240c 100644
--- a/requirements/portable/requirements_cpu_only_noavx2.txt
+++ b/requirements/portable/requirements_cpu_only_noavx2.txt
@@ -1,11 +1,10 @@
 audioop-lts<1.0; python_version >= "3.13"
 fastapi==0.112.4
-gradio==4.37.*
 html2text==2025.4.15
 jinja2==3.1.6
 markdown
 numpy==2.2.*
-pydantic==2.8.2
+pydantic==2.11.0
 PyPDF2==3.0.1
 python-docx==1.1.2
 pyyaml
@@ -13,11 +12,15 @@ requests
 rich
 tqdm
 
+# Gradio
+gradio==4.37.*
+https://github.com/oobabooga/gradio/releases/download/custom-build/gradio_client-1.0.2+custom.1-py3-none-any.whl
+
 # API
 flask_cloudflared==0.0.14
 sse-starlette==1.6.5
 tiktoken
 
 # llama.cpp (CPU only, no AVX2)
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"
diff --git a/requirements/portable/requirements_noavx2.txt b/requirements/portable/requirements_noavx2.txt
index ca66098c..857c5e66 100644
--- a/requirements/portable/requirements_noavx2.txt
+++ b/requirements/portable/requirements_noavx2.txt
@@ -1,11 +1,10 @@
 audioop-lts<1.0; python_version >= "3.13"
 fastapi==0.112.4
-gradio==4.37.*
 html2text==2025.4.15
 jinja2==3.1.6
 markdown
 numpy==2.2.*
-pydantic==2.8.2
+pydantic==2.11.0
 PyPDF2==3.0.1
 python-docx==1.1.2
 pyyaml
@@ -13,11 +12,15 @@ requests
 rich
 tqdm
 
+# Gradio
+gradio==4.37.*
+https://github.com/oobabooga/gradio/releases/download/custom-build/gradio_client-1.0.2+custom.1-py3-none-any.whl
+
 # API
 flask_cloudflared==0.0.14
 sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
diff --git a/requirements/portable/requirements_nowheels.txt b/requirements/portable/requirements_nowheels.txt
index be624bb1..1a7b5683 100644
--- a/requirements/portable/requirements_nowheels.txt
+++ b/requirements/portable/requirements_nowheels.txt
@@ -1,11 +1,10 @@
 audioop-lts<1.0; python_version >= "3.13"
 fastapi==0.112.4
-gradio==4.37.*
 html2text==2025.4.15
 jinja2==3.1.6
 markdown
 numpy==2.2.*
-pydantic==2.8.2
+pydantic==2.11.0
 PyPDF2==3.0.1
 python-docx==1.1.2
 pyyaml
@@ -13,6 +12,10 @@ requests
 rich
 tqdm
 
+# Gradio
+gradio==4.37.*
+https://github.com/oobabooga/gradio/releases/download/custom-build/gradio_client-1.0.2+custom.1-py3-none-any.whl
+
 # API
 flask_cloudflared==0.0.14
 sse-starlette==1.6.5
diff --git a/requirements/portable/requirements_vulkan.txt b/requirements/portable/requirements_vulkan.txt
index 36aff361..d2e66763 100644
--- a/requirements/portable/requirements_vulkan.txt
+++ b/requirements/portable/requirements_vulkan.txt
@@ -1,11 +1,10 @@
 audioop-lts<1.0; python_version >= "3.13"
 fastapi==0.112.4
-gradio==4.37.*
 html2text==2025.4.15
 jinja2==3.1.6
 markdown
 numpy==2.2.*
-pydantic==2.8.2
+pydantic==2.11.0
 PyPDF2==3.0.1
 python-docx==1.1.2
 pyyaml
@@ -13,11 +12,15 @@ requests
 rich
 tqdm
 
+# Gradio
+gradio==4.37.*
+https://github.com/oobabooga/gradio/releases/download/custom-build/gradio_client-1.0.2+custom.1-py3-none-any.whl
+
 # API
 flask_cloudflared==0.0.14
 sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+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 be7170e3..34927294 100644
--- a/requirements/portable/requirements_vulkan_noavx2.txt
+++ b/requirements/portable/requirements_vulkan_noavx2.txt
@@ -1,11 +1,10 @@
 audioop-lts<1.0; python_version >= "3.13"
 fastapi==0.112.4
-gradio==4.37.*
 html2text==2025.4.15
 jinja2==3.1.6
 markdown
 numpy==2.2.*
-pydantic==2.8.2
+pydantic==2.11.0
 PyPDF2==3.0.1
 python-docx==1.1.2
 pyyaml
@@ -13,11 +12,15 @@ requests
 rich
 tqdm
 
+# Gradio
+gradio==4.37.*
+https://github.com/oobabooga/gradio/releases/download/custom-build/gradio_client-1.0.2+custom.1-py3-none-any.whl
+
 # API
 flask_cloudflared==0.0.14
 sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.49.0/llama_cpp_binaries-0.49.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.53.0/llama_cpp_binaries-0.53.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"