2173 commits

Author	SHA1	Message	Date
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	27a6cdeec1	Fix multi-turn thinking block corruption for Kimi models	2026-03-17 11:31:55 -07:00
oobabooga	2d141b54c5	Fix several typos	2026-03-17 11:11:12 -07:00
oobabooga	249861b65d	web search: Update the user agents	2026-03-17 05:41:05 -07:00
oobabooga	dff8903b03	UI: Modernize the Gradio theme	2026-03-16 19:33:54 -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	737ded6959	Web search: Fix SSRF validation to block all non-global IPs	2026-03-16 05:37:46 -07:00
oobabooga	c0de1d176c	UI: Add an incognito chat option	2026-03-15 17:57:31 -07:00
oobabooga	92d376e420	web_search: Return all results and improve URL extraction	2026-03-15 13:14:53 -07:00
oobabooga	bfea49b197	Move top_p and top_k higher up in the UI and CLI help	2026-03-15 09:34:17 -07:00
oobabooga	80d0c03bab	llama.cpp: Change the default --fit-target from 1024 to 512	2026-03-15 09:29:25 -07:00
oobabooga	9119ce0680	llama.cpp: Use --fit-ctx 8192 when --fit on is used ... This sets the minimum acceptable context length, which by default is 4096.	2026-03-15 09:24:14 -07:00
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