Commit graph

5411 commits

Author SHA1 Message Date
weiguang li
952e2c404a
Bump sentence-transformers from 2.2.2 to 3.3.1 in superbooga (#7406) 2026-03-04 17:08:08 -03:00
oobabooga
cdf0e392e6 llama.cpp: Reorganize speculative decoding UI and use recommended ngram-mod defaults 2026-03-04 12:05:08 -08:00
oobabooga
eb90daf098 ExLlamaV2: Don't expose unused seed parameter 2026-03-04 11:14:50 -08:00
oobabooga
0ffb75de7c Update Transformers to 5.3.0 2026-03-04 11:12:54 -08:00
oobabooga
d8af0505a8 ExLlamav3_HF: Optimize prefill and fix CFG cache initialization 2026-03-04 11:09:58 -08:00
oobabooga
9b916f02cd ExLlamaV3: Attach AdaptiveP, fix speculative decoding parameter, add seed 2026-03-04 10:51:15 -08:00
oobabooga
5d93f4e800 Fix requires_grad warning in logits API 2026-03-04 10:43:23 -08:00
oobabooga
64eb77e782 Fix the logits API endpoint with transformers 2026-03-04 10:41:47 -08:00
oobabooga
22141679e3 Update the custom gradio wheels 2026-03-04 10:01:31 -08:00
oobabooga
65de4c30c8 Add adaptive-p sampler and n-gram speculative decoding support 2026-03-04 09:41:29 -08:00
oobabooga
f010aa1612 Replace PyPDF2 with pymupdf for PDF text extraction
pymupdf produces cleaner text (e.g. no concatenated words in headers),
handles encrypted and malformed PDFs that PyPDF2 failed on, and
supports non-Latin scripts.
2026-03-04 06:43:37 -08:00
oobabooga
f4d787ab8d Delegate GPU layer allocation to llama.cpp's --fit 2026-03-04 06:37:50 -08:00
oobabooga
8a3d866401 Fix temperature_last having no effect in llama.cpp server sampler order 2026-03-04 06:10:51 -08:00
oobabooga
11dc6fdfce Update the custom gradio wheels 2026-03-04 06:04:33 -08:00
oobabooga
7d42b6900e Update the custom gradio wheels 2026-03-04 05:47:59 -08:00
oobabooga
8cbb7661a8 Remove no longer needed dark theme localstorage code 2026-03-03 18:51:24 -08:00
oobabooga
866c48e55b Simplify dark theme handling using gradio fork's new dark_theme parameter 2026-03-03 18:41:47 -08:00
oobabooga
b3fd0d16e0 Use a new gr.Headless component for efficient chat streaming 2026-03-03 18:12:03 -08:00
oobabooga
d584ede72e Avoid a circular import 2026-03-03 17:59:47 -08:00
oobabooga
c0bff831e3 Update custom gradio wheels 2026-03-03 17:21:18 -08:00
oobabooga
2260e530c9 Remove gradio monkey-patches (moved to gradio fork) 2026-03-03 17:17:36 -08:00
oobabooga
e9f22813e4 Replace gradio with my gradio 4.37.2 fork 2026-03-03 16:51:27 -08:00
dependabot[bot]
3519890c8e
Bump flask-cloudflared from 0.0.14 to 0.0.15 in /requirements/full (#7380) 2026-03-03 21:41:51 -03:00
dependabot[bot]
9c604628a0
Bump flask-cloudflared from 0.0.14 to 0.0.15 in /requirements/portable (#7382) 2026-03-03 21:41:46 -03:00
oobabooga
fbd2acfa19 Remove triton-windows from non-CUDA requirements 2026-03-03 16:16:55 -08:00
oobabooga
5fd79b23d1 Add CUDA 13.1 portable builds 2026-03-03 15:36:41 -08:00
oobabooga
b8fcc8ea32 Update llama.cpp, remove noavx2 builds, add ROCm Windows portable builds 2026-03-03 15:27:19 -08:00
Pádraic Slattery
d7dd533b99
chore: Update outdated GitHub Actions versions (#7384) 2026-03-03 17:54:12 -03:00
oobabooga
9576c5a5f4 Update Miniforge from 25.3.0 to 26.1.0 2026-03-03 12:33:20 -08:00
oobabooga
9814d3d0ae Patch gradio 4.x for huggingface-hub 1.x compatibility 2026-03-03 12:20:37 -08:00
oobabooga
38d0eeefc0 Update dependencies: torch 2.9.1, transformers 5.2, exllamav3 0.0.22, accelerate 1.12, huggingface-hub 1.5 2026-03-03 12:01:02 -08:00
oobabooga
ddd74324fe Update PyTorch to 2.9.1 and ROCm to 6.4 2026-03-03 11:38:52 -08:00
oobabooga
efc72d5c32 Update Python from 3.11 to 3.13 2026-03-03 11:03:26 -08:00
oobabooga
aecbc5a8ac Merge remote-tracking branch 'refs/remotes/origin/dev' into dev 2026-01-28 08:30:28 -08:00
oobabooga
c54e8a2b3d Try to spawn llama.cpp on port 5001 instead of random port 2026-01-28 08:23:55 -08:00
oobabooga
dc2bbf1861 Refactor thinking block detection and add Solar Open support 2026-01-28 08:21:34 -08:00
dependabot[bot]
cae1fef42d
Bump triton-windows in /requirements/full (#7368) 2026-01-14 21:30:59 -03:00
q5sys (JT)
7493fe7841
feat: Add a dropdown to save/load user personas (#7367) 2026-01-14 20:35:08 -03:00
jakubartur
21b979c02a
Fix code block copy button on HTTP (Clipboard API fallback) (#7358) 2026-01-14 19:34:21 -03:00
oobabooga
a731861127 Update README 2026-01-13 15:38:32 -08:00
oobabooga
910456ba31
Merge pull request #7366 from oobabooga/dev
Merge dev branch
2026-01-08 17:54:12 -03:00
oobabooga
d79cdc614c Update llama.cpp 2026-01-08 11:24:15 -08:00
oobabooga
332fd40653 Update llama.cpp 2026-01-07 19:06:23 -08:00
dependabot[bot]
50a35b483c
Update bitsandbytes requirement in /requirements/full (#7353) 2026-01-06 15:27:23 -03:00
dependabot[bot]
45fbec0320
Update torchao requirement in /requirements/full (#7356) 2026-01-06 15:27:10 -03:00
oobabooga
b0968ed8b4 Update flash-linear-attention 2026-01-06 10:26:43 -08:00
oobabooga
36747cf99c Lint 2026-01-06 10:24:34 -08:00
oobabooga
2fcbadec67 Merge remote-tracking branch 'refs/remotes/origin/dev' into dev 2026-01-06 10:24:07 -08:00
oobabooga
bb3b7bc197 Update llama.cpp 2026-01-06 10:23:58 -08:00
Sergey 'Jin' Bostandzhyan
6e2c4e9c23
Fix loading models which have their eos token disabled (#7363) 2026-01-06 11:31:10 -03:00