oobabooga
|
2ca61f21fb
|
Cleanup modules/web_search.py
|
2026-05-02 19:19:19 -07:00 |
|
oobabooga
|
d38124bee2
|
Update README
|
2026-05-02 19:08:25 -07:00 |
|
oobabooga
|
25d600424a
|
Update README
|
2026-05-02 19:06:20 -07:00 |
|
oobabooga
|
365848f432
|
Update README
|
2026-05-02 19:05:19 -07:00 |
|
oobabooga
|
3f97f5c3ce
|
Update README
|
2026-05-02 19:04:09 -07:00 |
|
oobabooga
|
9c85092c60
|
Update README
|
2026-05-02 19:02:50 -07:00 |
|
oobabooga
|
8376284d7a
|
Fix extension settings not saving for user_data/extensions (closes #7525)
|
2026-05-02 18:54:49 -07:00 |
|
oobabooga
|
717b17c49c
|
Update README
|
2026-05-02 18:51:30 -07:00 |
|
oobabooga
|
7facf669f8
|
Replace DuckDuckGo scraping with ddgs library
|
2026-05-02 18:50:22 -07:00 |
|
oobabooga
|
30177bbd36
|
Improve the chat Stop button
|
2026-05-02 18:20:40 -07:00 |
|
oobabooga
|
a4838aedbc
|
Update README
|
2026-05-02 16:13:16 -07:00 |
|
oobabooga
|
d9a83d8fd9
|
Add missing electronjs file + small fixes
|
2026-05-02 15:51:55 -07:00 |
|
oobabooga
|
8e7ecabc68
|
Update llama.cpp
|
2026-05-02 11:26:23 -07:00 |
|
oobabooga
|
03b964a3e5
|
Minor color improvement
|
2026-05-02 09:25:11 -07:00 |
|
oobabooga
|
8e0b02a169
|
Fix Stop button being ignored during tool call approval
|
2026-05-02 08:26:38 -07:00 |
|
oobabooga
|
ddec64af71
|
UI: refinements after c6a57a4572 & electron user_data path
|
2026-05-02 08:18:39 -07:00 |
|
oobabooga
|
cfda0991ce
|
Add Electron desktop app to portable builds
|
2026-05-01 23:15:58 -07:00 |
|
oobabooga
|
c6a57a4572
|
Major UI overhaul
|
2026-05-01 22:06:18 -07:00 |
|
oobabooga
|
54c4feeb4f
|
Support .jinja/.jinja2 instruction template files in the UI (closes #7517)
|
2026-04-26 18:57:07 -07:00 |
|
oobabooga
|
4b575a2fae
|
llama.cpp: Add --split-mode flag with tensor parallelism support
|
2026-04-26 17:44:32 -07:00 |
|
oobabooga
|
187b07a924
|
Fix race condition and clean up exllamav3 module
|
2026-04-25 15:14:44 -07:00 |
|
oobabooga
|
08b53f856e
|
Merge branch 'main' into dev
|
2026-04-23 12:25:17 -07:00 |
|
oobabooga
|
c014efd59a
|
Update transformers to 5.6
|
2026-04-23 11:44:54 -07:00 |
|
oobabooga
|
d31662a410
|
Revert "Pre-load MCP stdio server tools at startup"
This reverts commit dc798aabe3.
|
2026-04-23 07:53:42 -07:00 |
|
oobabooga
|
dc798aabe3
|
Pre-load MCP stdio server tools at startup
|
2026-04-23 06:37:20 -07:00 |
|
oobabooga
|
d440d837b5
|
Update the custom gradio wheels
|
2026-04-23 06:25:39 -07:00 |
|
oobabooga
|
1d1a319597
|
llama.cpp: Fix multimodal by using server's random media marker
|
2026-04-23 06:21:19 -07:00 |
|
oobabooga
|
5a9d61edc5
|
Update llama.cpp
|
2026-04-22 18:54:41 -07:00 |
|
oobabooga
|
8ac5162cbf
|
Update README
|
2026-04-22 18:52:18 -07:00 |
|
oobabooga
|
7338120bff
|
Fix GPT-OSS channel tokens leaking in UI after tool calls
|
2026-04-22 18:08:59 -07:00 |
|
oobabooga
|
1bb6ae4fe6
|
Update README
|
2026-04-22 16:02:03 -07:00 |
|
oobabooga
|
cb023a9897
|
Follow-up to a253d38953
|
2026-04-22 15:36:07 -07:00 |
|
oobabooga
|
1d871c0896
|
Fix Gemma 4 thinking tags not hidden after tool calls (closes #7509)
|
2026-04-22 15:17:17 -07:00 |
|
oobabooga
|
4737744f4a
|
Security: Fix SSRF vulnerabilities in URL fetching
|
2026-04-22 14:43:16 -07:00 |
|
oobabooga
|
83347ed7e4
|
Add preserve_thinking chat template parameter (UI and CLI)
|
2026-04-22 13:43:56 -07:00 |
|
oobabooga
|
9a9f3ae9e8
|
llama.cpp: Pass --draft-min 48 by default for draftless speculative decoding
|
2026-04-22 13:00:48 -07:00 |
|
oobabooga
|
4e065e6a65
|
Update llama.cpp
|
2026-04-22 12:50:04 -07:00 |
|
oobabooga
|
a253d38953
|
Add tool call confirmation with inline approve/reject buttons
|
2026-04-22 11:49:39 -07:00 |
|
oobabooga
|
1e1d2d3728
|
Cache MCP tool discovery to avoid re-querying on each generation
|
2026-04-22 09:45:51 -07:00 |
|
oobabooga
|
707b5df4ea
|
Add stdio MCP server support via user_data/mcp.json
|
2026-04-19 20:47:59 -07:00 |
|
oobabooga
|
1b3af51dc5
|
Update exllamav3 to v0.0.30, pin xformers
|
2026-04-19 11:39:00 -07:00 |
|
oobabooga
|
eb596b8e0a
|
Update llama.cpp
|
2026-04-18 17:13:04 -07:00 |
|
oobabooga
|
6f3b1b0369
|
UI: Only show reasoning effort/enable thinking for models that use them
|
2026-04-18 13:45:35 -07:00 |
|
oobabooga
|
beb6e17ac7
|
UI: Fix code block scrollbar flash during page load
|
2026-04-18 11:53:37 -07:00 |
|
oobabooga
|
ae997d6a36
|
UI: Remove fixed sidebar positioning on wide viewports
This made the main chat scrollbar disappear behind the
right sidebar on desktop.
|
2026-04-18 11:42:27 -07:00 |
|
oobabooga
|
40ba6109e0
|
UI: Improve border colors in light theme
|
2026-04-18 10:38:55 -07:00 |
|
oobabooga
|
145f3297a2
|
UI: Sidebar defaults based on viewport width
|
2026-04-16 03:51:12 -07:00 |
|
oobabooga
|
78a178de9e
|
UI: Past chats menu improvement
|
2026-04-16 03:32:44 -07:00 |
|
oobabooga
|
21d4c17444
|
UI: Fix code block copy button centering and light/dark mode colors
|
2026-04-15 20:01:42 -07:00 |
|
oobabooga
|
acb2488acf
|
UI: Make sidebars toggle independently, overlay the chat area, and persist state on page refresh
|
2026-04-15 19:43:56 -07:00 |
|
oobabooga
|
57be34d7a6
|
Fix bos/eos tokens being overwritten after GGUF metadata sets them (closes #7496)
|
2026-04-15 13:14:27 -07:00 |
|
oobabooga
|
a56e281204
|
Clean up unused function
|
2026-04-15 11:34:29 -07:00 |
|
oobabooga
|
dd77820a3a
|
UI: Fix consecutive thinking blocks rendering with Gemma 4
|
2026-04-15 11:24:25 -07:00 |
|
oobabooga
|
e4168ee8b8
|
Fix tool responses with Gemma 4 template (closes #7498)
|
2026-04-15 08:56:57 -07:00 |
|
oobabooga
|
5992fa9044
|
Fix "Start reply with" crash (closes #7497)
|
2026-04-15 08:12:35 -07:00 |
|
oobabooga
|
f66a01bd06
|
UI: Add an error message when no model is loaded
|
2026-04-14 21:05:56 -07:00 |
|
oobabooga
|
734d3c38a0
|
Reset bos/eos tokens to defaults before reading model metadata
|
2026-04-14 20:30:29 -07:00 |
|
oobabooga
|
b06b36a6a6
|
Lint
|
2026-04-14 20:28:55 -07:00 |
|
oobabooga
|
4e978dd037
|
Update README
|
2026-04-14 20:23:16 -07:00 |
|
oobabooga
|
4bce4a38fc
|
Attempt at fixing chat scroll getting stuck on thinking blocks (#7485)
|
2026-04-15 00:08:08 -03:00 |
|
oobabooga
|
2aee3a1898
|
UI: Deduplicate auto-scroll calls with queueMicrotask
|
2026-04-15 00:08:06 -03:00 |
|
oobabooga
|
160a5e1a61
|
Merge remote-tracking branch 'refs/remotes/origin/dev' into dev
|
2026-04-14 19:21:19 -07:00 |
|
oobabooga
|
9e323425d8
|
Fix row_split not working with ik_llama.cpp (closes #7489)
|
2026-04-14 23:18:36 -03:00 |
|
oobabooga
|
a8a0f8dc82
|
Fix version metadata not syncing on Continue (closes #7492)
|
2026-04-14 23:13:58 -03:00 |
|
oobabooga
|
533b43640b
|
Revert "Update exllamav3"
This reverts commit e9d7feb151.
|
2026-04-14 22:07:20 -03:00 |
|
oobabooga
|
3dcb30b970
|
Update llama.cpp
|
2026-04-14 17:55:46 -07:00 |
|
oobabooga
|
5f16b86db0
|
Update README
|
2026-04-14 11:44:26 -07:00 |
|
oobabooga
|
65cef2c731
|
Rename project from text-generation-webui to textgen
|
2026-04-13 17:03:19 -03:00 |
|
oobabooga
|
61bfc2ffd5
|
Update README
|
2026-04-13 12:14:59 -07:00 |
|
oobabooga
|
a9afc48ba7
|
Merge remote-tracking branch 'refs/remotes/origin/dev' into dev
|
2026-04-13 10:48:12 -07:00 |
|
oobabooga
|
1ae749ac76
|
Merge branch 'main' into dev
|
2026-04-13 10:48:03 -07:00 |
|
oobabooga
|
add91613db
|
Fix bos/eos tokens not being set for models without a chat template
|
2026-04-12 16:01:00 -07:00 |
|
oobabooga
|
e9d7feb151
|
Update exllamav3
|
2026-04-11 21:29:46 -07:00 |
|
oobabooga
|
456afad585
|
Update llama.cpp
|
2026-04-11 15:42:31 -07:00 |
|
oobabooga
|
326867e799
|
Reduce VRAM peak in prompt logprobs forward pass
|
2026-04-10 19:21:57 -07:00 |
|
oobabooga
|
9bc3f9f3dd
|
Update README
|
2026-04-10 12:21:48 -07:00 |
|
oobabooga
|
24cc0e2236
|
Update llama.cpp
|
2026-04-10 08:38:59 -07:00 |
|
oobabooga
|
5ad199e9bb
|
Update README
|
2026-04-08 14:20:24 -07:00 |
|
oobabooga
|
e18f32cba7
|
Remove hardcoded trust_remote_code=True in embedding loader
|
2026-04-06 17:47:50 -07:00 |
|
oobabooga
|
778e1c4d52
|
Update llama.cpp/ik_llama.cpp
|
2026-04-06 17:04:49 -07:00 |
|
oobabooga
|
775c913de2
|
Fix crash when truncating prompts with tool call messages
|
2026-04-06 14:13:01 -07:00 |
|
oobabooga
|
cb511928e2
|
Fix GPT-OSS tag leak during streaming between thinking and tool calls
|
2026-04-06 12:06:28 -07:00 |
|
oobabooga
|
193424cc93
|
API: Fix IPv6 address formatting
|
2026-04-06 10:07:52 -07:00 |
|
oobabooga
|
c26ffdd24c
|
API: add instruction_template support to the model load endpoint
|
2026-04-06 07:02:53 -07:00 |
|
oobabooga
|
4d6230a944
|
Follow-up to d78fc46114
|
2026-04-06 06:48:48 -07:00 |
|
oobabooga
|
7b2f15e34a
|
Minor change after b1d06dcf96
|
2026-04-05 21:16:32 -07:00 |
|
oobabooga
|
05e4842033
|
Fix image generation: default to SDPA attention backend
|
2026-04-05 20:03:06 -07:00 |
|
oobabooga
|
b1d06dcf96
|
UI: Add MCP server support
|
2026-04-05 19:46:01 -07:00 |
|
oobabooga
|
abc3487f4d
|
UI: Move cpu-moe checkbox to extra flags (no longer useful now that --fit exists)
|
2026-04-05 18:24:26 -07:00 |
|
oobabooga
|
223dd4b801
|
UI: Hide spin buttons on number inputs
|
2026-04-05 18:22:50 -07:00 |
|
oobabooga
|
f8db23b362
|
Call ik portable build folders text-generation-webui-ik-version
|
2026-04-05 17:12:28 -07:00 |
|
oobabooga
|
d78fc46114
|
Fix "address already in use" on server restart (Linux/macOS)
|
2026-04-05 16:42:27 -07:00 |
|
oobabooga
|
422f42ca7f
|
Pre-compile LaTeX regex in html_generator.py
|
2026-04-04 23:51:15 -07:00 |
|
oobabooga
|
544fcb0b7f
|
Simplify modules/image_models.py
|
2026-04-04 23:29:57 -07:00 |
|
oobabooga
|
c63a79ee48
|
Image generation: Embed generation metadata in API image responses
|
2026-04-04 23:15:14 -07:00 |
|
oobabooga
|
9805ddcde9
|
Update the custom gradio wheels
|
2026-04-04 21:34:09 -07:00 |
|
oobabooga
|
91f9b01516
|
UI: Minor change
|
2026-04-04 21:13:20 -07:00 |
|
oobabooga
|
1f49a64e1a
|
UI: Improve blockquote border width and color
|
2026-04-04 20:44:37 -07:00 |
|
oobabooga
|
e8b31c063a
|
UI: Soften message action icons in light mode
|
2026-04-04 20:38:31 -07:00 |
|
oobabooga
|
ee917cd5ed
|
UI: Make table and hr borders more subtle
|
2026-04-04 20:35:27 -07:00 |
|