oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-03-18 03:14:39 +01:00
Code Issues Actions Packages Projects Releases Wiki Activity
5372 commits 2 branches 94 tags 70 MiB
Commit graph

2087 commits

Author SHA1 Message Date
oobabooga e0a38da9f3 Improve tool call parsing for Devstral/GPT-OSS and preserve thinking across tool turns 2026-03-13 11:04:06 -03:00
oobabooga c39c187f47 UI: Improve the style of table scrollbars 2026-03-13 03:21:47 -07:00
oobabooga c094bc943c UI: Skip output extensions on intermediate tool-calling turns 2026-03-12 21:45:38 -07:00
oobabooga 85ec85e569 UI: Fix Continue while in a tool-calling loop, remove the upper limit on number of tool calls 2026-03-12 20:22:35 -07:00
oobabooga 04213dff14 Address copilot feedback 2026-03-12 19:55:20 -07:00
oobabooga 58f26a4cc7 UI: Skip redundant work in chat loop when no tools are selected 2026-03-12 19:18:55 -07:00
oobabooga 286ae475f6 UI: Clean up tool calling code 2026-03-12 22:39:38 -03:00
oobabooga a09f21b9de UI: Fix tool calling for GPT-OSS and Continue 2026-03-12 22:17:20 -03:00
oobabooga 5c02b7f603 Allow the fetch_webpage tool to return links 2026-03-12 17:08:30 -07:00
oobabooga 09d5e049d6 UI: Improve the Tools checkbox list style 2026-03-12 16:53:49 -07:00
oobabooga 4f82b71ef3 UI: Bump the ctx-size max from 131072 to 262144 (256K) 2026-03-12 14:56:35 -07:00
oobabooga bbd43d9463 UI: Correctly propagate truncation_length when ctx_size is auto 2026-03-12 14:54:05 -07:00
oobabooga 3e6bd1a310 UI: Prepend thinking tag when template appends it to prompt 
Makes Qwen models have a thinking block straight away during streaming.
 2026-03-12 14:30:51 -07:00
oobabooga 9a7428b627 UI: Add collapsible accordions for tool calling steps 2026-03-12 14:16:04 -07:00
oobabooga 2d0cc7726e API: Add reasoning_content field to non-streaming chat completions 
Extract thinking/reasoning blocks (e.g. <think>...</think>) into a
separate reasoning_content field on the assistant message, matching
the convention used by DeepSeek, llama.cpp, and SGLang.
 2026-03-12 16:30:46 -03:00
oobabooga a916fb0e5c API: Preserve mid-conversation system message positions 2026-03-12 14:27:24 -03:00
oobabooga fb1b3b6ddf API: Rewrite logprobs for OpenAI spec compliance across all backends 
- Rewrite logprobs output format to match the OpenAI specification for
  both chat completions and completions endpoints
- Fix top_logprobs count being ignored for llama.cpp and ExLlamav3
  backends in chat completions (always returned 1 instead of requested N)
- Fix non-streaming responses only returning logprobs for the last token
  instead of all generated tokens (affects all HF-based loaders)
- Fix logprobs returning null for non-streaming chat requests on HF loaders
- Fix off-by-one returning one extra top alternative on HF loaders
 2026-03-12 14:17:32 -03:00
oobabooga 4b6c9db1c9 UI: Fix stale tool_sequence after edit and chat-instruct tool rendering 2026-03-12 13:12:18 -03:00
oobabooga b5cac2e3b2 Fix swipes and edit for tool calling in the UI 2026-03-12 01:53:37 -03:00
oobabooga 0d62038710 Add tools refresh button and _tool_turn comment 2026-03-12 01:36:07 -03:00
oobabooga cf9ad8eafe Initial tool-calling support in the UI 2026-03-12 01:16:19 -03:00
oobabooga 980a9d1657 UI: Minor defensive changes to autosave 2026-03-11 15:50:16 -07:00
oobabooga bb00d96dc3 Use a new gr.DragDrop element for Sampler priority + update gradio 2026-03-11 19:35:12 -03:00
oobabooga 3304b57bdf Add native logit_bias and logprobs support for ExLlamav3 2026-03-10 11:03:25 -03:00
oobabooga 8aeaa76365 Forward logit_bias, logprobs, and n to llama.cpp backend 
- Forward logit_bias and logprobs natively to llama.cpp
- Support n>1 completions with seed increment for diversity
- Fix logprobs returning empty dict when not requested
 2026-03-10 10:41:45 -03:00
oobabooga 6ec4ca8b10 Add missing custom_token_bans to llama.cpp and reasoning_effort to ExLlamav3 2026-03-10 09:58:00 -03:00
oobabooga 307c085d1b Minor warning change 2026-03-09 21:44:53 -07:00
oobabooga c604ca66de Update the --multi-user warning 2026-03-09 21:36:04 -07:00
oobabooga 7f485274eb Fix ExLlamaV3 EOS handling, load order, and perplexity evaluation 
- Use config.eos_token_id_list for all EOS tokens as stop conditions
  (fixes models like Llama-3 that define multiple EOS token IDs)
- Load vision/draft models before main model so autosplit accounts
  for their VRAM usage
- Fix loss computation in ExLlamav3_HF: use cache across chunks so
  sequences longer than 2048 tokens get correct perplexity values
 2026-03-09 23:56:38 -03:00
oobabooga 39e6c997cc Refactor to not import gradio in --nowebui mode 2026-03-09 19:29:24 -07:00
oobabooga 40f1837b42 README: Minor updates 2026-03-08 08:38:29 -07:00
oobabooga f6ffecfff2 Add guard against training with llama.cpp loader 2026-03-08 10:47:59 -03:00
oobabooga 5a91b8462f Remove ctx_size_draft from ExLlamav3 loader 2026-03-08 09:53:48 -03:00
oobabooga 7a8ca9f2b0 Fix passing adaptive-p to llama-server 2026-03-08 04:09:40 -07:00
oobabooga baf4e13ff1 ExLlamav3: fix draft cache size to match main cache 2026-03-07 22:34:48 -03:00
oobabooga 6ff111d18e ExLlamav3: handle exceptions in ConcurrentGenerator iterate loop 2026-03-07 22:05:31 -03:00
oobabooga 304510eb3d ExLlamav3: route all generation through ConcurrentGenerator 2026-03-07 05:54:14 -08:00
oobabooga abc699db9b Minor UI change 2026-03-06 19:03:38 -08:00
oobabooga 7ea5513263 Handle Qwen 3.5 thinking blocks 2026-03-06 19:01:28 -08:00
oobabooga 5fa709a3f4 llama.cpp server: use port+5 offset and suppress No parser definition detected logs 2026-03-06 18:52:34 -08:00
oobabooga 1eead661c3 Portable mode: always use ../user_data if it exists 2026-03-06 18:04:48 -08:00
oobabooga d48b53422f Training: Optimize _peek_json_keys to avoid loading entire file into memory 2026-03-06 15:39:08 -08:00
oobabooga 5f6754c267 Fix stop button being ignored when token throttling is off 2026-03-06 17:12:34 -03:00
oobabooga b8b4471ab5 Security: restrict file writes to user_data_dir, block extra_flags from API 2026-03-06 16:58:11 -03:00
oobabooga d03923924a Several small fixes 
- Stop llama-server subprocess on model unload instead of relying on GC
- Fix tool_calls[].index being string instead of int in API responses
- Omit tool_calls key from API response when empty per OpenAI spec
- Prevent division by zero when micro_batch_size > batch_size in training
- Copy sampler_priority list before mutating in ExLlamaV3
- Normalize presence/frequency_penalty names for ExLlamaV3 sampler sorting
- Restore original chat_template after training instead of leaving it mutated
 2026-03-06 16:52:13 -03:00
oobabooga 044566d42d API: Add tool call parsing for DeepSeek, GLM, MiniMax, and Kimi models 2026-03-06 15:06:56 -03:00
oobabooga f5acf55207 Add --chat-template-file flag to override the default instruction template for API requests 
Matches llama.cpp's flag name. Supports .jinja, .jinja2, and .yaml files.
Priority: per-request params > --chat-template-file > model's built-in template.
 2026-03-06 14:04:16 -03:00
oobabooga 93ebfa2b7e Fix llama-server output filter for new log format 2026-03-06 02:38:13 -03:00
oobabooga eba262d47a Security: prevent path traversal in character/user/file save and delete 2026-03-06 02:00:10 -03:00
oobabooga 66fb79fe15 llama.cpp: Add --fit-target param 2026-03-06 01:55:48 -03:00