Commit graph

5458 commits

Author SHA1 Message Date
oobabooga f2c909725e API: Use top_p=0.95 by default 2026-03-21 11:11:09 -07:00
oobabooga 0216893475 API: Add Anthropic-compatible /v1/messages endpoint 2026-03-20 20:38:55 -07:00
oobabooga f0e3997f37 Add missing __init__.py to modules/grammar 2026-03-20 16:04:57 -03:00
oobabooga 7c79143a14 API: Fix _start_cloudflared raising after first attempt instead of exhausting retries 2026-03-20 15:03:49 -03:00
oobabooga 855141967c API: Handle --extensions openai as alias for --api 2026-03-20 15:03:17 -03:00
oobabooga 1a910574c3 API: Fix debug_msg truthy check for OPENEDAI_DEBUG=0 2026-03-20 14:57:01 -03:00
oobabooga bf6fbc019d API: Move OpenAI-compatible API from extensions/openai to modules/api 2026-03-20 14:46:00 -03:00
oobabooga 2e4232e02b Minor cleanup 2026-03-20 07:20:26 -07:00
oobabooga 843de8b8a8 Update exllamav3 to 0.0.26 2026-03-19 18:49:36 -07:00
oobabooga b3eb0e313d Reduce the size of portable builds by using stripped Python 2026-03-19 11:53:12 -07:00
oobabooga b9922f71ba Merge branch 'main' into dev 2026-03-19 08:05:01 -07:00
oobabooga e0e20ab9e7 Minor cleanup across multiple modules 2026-03-19 08:02:23 -07:00
oobabooga 5453b9f30e Remove ancient/obsolete instruction templates 2026-03-19 07:54:37 -07:00
oobabooga dde1764763 Cleanup modules/chat.py 2026-03-18 21:12:14 -07:00
oobabooga 779e7611ff Use logger.exception() instead of traceback.print_exc() for error messages 2026-03-18 20:42:20 -07:00
oobabooga eeb0e5700f Fix AMD installer failing to resolve ROCm triton dependency
Closes #7436
2026-03-18 09:15:40 -07:00
oobabooga ca36bd6eb6 API: Remove leading spaces from post-reasoning content 2026-03-18 07:36:11 -07:00
oobabooga fef2bd8630 UI: Fix the instruction template delete dialog not appearing 2026-03-17 22:52:32 -07:00
oobabooga 256431f258 Security: server-side file save roots, image URL SSRF protection, extension allowlist 2026-03-17 22:31:20 -07:00
oobabooga c8bb2129ba Security: server-side file save roots, image URL SSRF protection, extension allowlist 2026-03-17 22:29:35 -07:00
oobabooga 08ff3f0f90 Merge remote-tracking branch 'refs/remotes/origin/dev' into dev 2026-03-17 19:52:24 -07:00
oobabooga 7e54e7b7ae llama.cpp: Support literal flags in --extra-flags (e.g. --rpc, --jinja)
The old format is still accepted for backwards compatibility.
2026-03-17 19:47:55 -07:00
oobabooga 2a6b1fdcba Fix --extra-flags breaking short long-form-only flags like --rpc
Closes #7357
2026-03-17 18:29:15 -07:00
Alvin Tang 73a094a657
Fix file handle leaks and redundant re-read in get_model_metadata (#7422) 2026-03-17 22:06:05 -03:00
RoomWithOutRoof f0014ab01c
fix: mutable default argument in LogitsBiasProcessor (#7426) 2026-03-17 22:03:48 -03:00
oobabooga 0f5053c0fb requirements: Update pymupdf 2026-03-17 17:59:06 -07:00
oobabooga 27a6cdeec1 Fix multi-turn thinking block corruption for Kimi models 2026-03-17 11:31:55 -07:00
oobabooga 3f36189fa0 Merge remote-tracking branch 'refs/remotes/origin/dev' into dev 2026-03-17 11:16:20 -07:00
oobabooga 2d141b54c5 Fix several typos 2026-03-17 11:11:12 -07:00
Raunak-Kumar7 fffcd20f4d
superboogav2: Fix broken delete endpoint (#6010) 2026-03-17 14:44:54 -03:00
oobabooga 249861b65d web search: Update the user agents 2026-03-17 05:41:05 -07:00
oobabooga 5992e088fa Update the custom gradio wheels 2026-03-16 19:34:37 -07:00
oobabooga dff8903b03 UI: Modernize the Gradio theme 2026-03-16 19:33:54 -07:00
oobabooga 9d02d3a13b docs: Minor change to tool calling tutorial 2026-03-16 16:10:17 -07:00
oobabooga 238cbd5656 training: Remove arbitrary higher_rank_limit parameter 2026-03-16 16:05:43 -07:00
oobabooga 22ff5044b0 training: Organize the UI 2026-03-16 16:01:40 -07:00
oobabooga 1c89376370 training: Add gradient_checkpointing for lower VRAM by default 2026-03-16 15:23:24 -07:00
oobabooga 88a318894c
Merge pull request #7425 from oobabooga/dev
Merge dev branch
2026-03-16 12:51:33 -03:00
oobabooga 44810751de Update llama.cpp 2026-03-16 06:21:14 -07:00
oobabooga 6c05a964a7 docs: Mention supported tool-calling models 2026-03-16 06:00:16 -07:00
oobabooga 737ded6959 Web search: Fix SSRF validation to block all non-global IPs 2026-03-16 05:37:46 -07:00
oobabooga 50685c93f2 Update README 2026-03-16 05:29:27 -07:00
oobabooga 9d9f5d9860 Update README 2026-03-15 20:27:44 -07:00
oobabooga 5cfe9fe295 Update README 2026-03-15 20:12:22 -07:00
oobabooga b76a289e04 API: Respect --listen-host for the OpenAI API server
Closes #7429
2026-03-15 18:04:34 -07:00
oobabooga c0de1d176c UI: Add an incognito chat option 2026-03-15 17:57:31 -07:00
oobabooga 4f80b20859 UI: Follow-up to beab346f (fix scroll deadlock on chat-parent) 2026-03-15 16:38:54 -07:00
oobabooga f8ff7cf99e Update the custom gradio wheels 2026-03-15 14:12:59 -07:00
oobabooga 92d376e420 web_search: Return all results and improve URL extraction 2026-03-15 13:14:53 -07:00
oobabooga f6a749a151 API: Fix /v1/models to only list the currently loaded model 2026-03-15 10:17:31 -07:00