oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-03-18 11:24:39 +01:00
Code Issues Actions Packages Projects Releases Wiki Activity
5404 commits 2 branches 95 tags 70 MiB
Commit graph

2104 commits

Author SHA1 Message Date
oobabooga 5763cab3c4 Fix a crash loading the MiniMax-M2.5 jinja template 2026-03-15 07:13:26 -07:00
oobabooga f0c16813ef Remove the rope scaling parameters 
Now models have 131k+ context length. The parameters can still be
passed to llama.cpp through --extra-flags.
 2026-03-14 19:43:25 -07:00
oobabooga 2d3a3794c9 Add a Top-P preset, make it the new default, clean up the built-in presets 2026-03-14 19:22:12 -07:00
oobabooga b9bdbd638e Fix after 4ae2bd86e2 2026-03-14 18:18:33 -07:00
oobabooga e11425d5f8 Fix relative redirect handling in web page fetcher 2026-03-14 15:46:21 -07:00
oobabooga 4ae2bd86e2 Change the default ctx-size to 0 (auto) for llama.cpp 2026-03-14 15:30:01 -07:00
oobabooga 573617157a Optimize tool call detection 
Avoids templates that don't contain a given necessary keyword
 2026-03-14 12:09:41 -07:00
oobabooga d0a4993cf4 UI: Increase ctx-size slider maximum to 1M and step to 1024 2026-03-14 09:53:12 -07:00
oobabooga c908ac00d7 Replace html2text with trafilatura for better web content extraction 
After this change a lot of boilerplate is removed from web pages, saving tokens on agentic loops.
 2026-03-14 09:29:17 -07:00
oobabooga 8bff331893 UI: Fix tool call markup flashing before accordion appears during streaming 2026-03-14 09:26:20 -07:00
oobabooga cb08ba63dc Fix GPT-OSS channel markup leaking into UI when model skips analysis block 2026-03-14 09:08:05 -07:00
oobabooga 09a6549816 API: Stream reasoning_content separately from content in OpenAI-compatible responses 2026-03-14 06:52:40 -07:00
oobabooga accb2ef661 UI/API: Prevent tool call markup from leaking into streamed UI output (closes #7427) 2026-03-14 06:26:47 -07:00
oobabooga e8d1c66303 Clean up tool calling code 2026-03-13 18:27:01 -07:00
oobabooga 24e7e77b55 Clean up 2026-03-13 12:37:10 -07:00
oobabooga 5362bbb413 Make web_search not download the page contents, use fetch_webpage instead 2026-03-13 12:09:08 -07:00
oobabooga aab2596d29 UI: Fix multiple thinking blocks rendering as raw text in HTML generator 2026-03-13 15:47:11 -03:00
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