Commit Graph

3005 Commits

Author SHA1 Message Date
Jiang-Jia-Jun
f57422e3c1 Update serving parameters description 2025-06-10 19:27:38 +08:00
Jiang-Jia-Jun
0dcfc6de75 Polish README.md 2025-06-10 17:17:34 +08:00
jiangjiajun
041919b343 Remove unavailable doc link 2025-06-10 11:02:37 +08:00
jiangjiajun
b03fb36873 Provide prebuilt docker image 2025-06-10 10:28:54 +08:00
jiangjiajun
26dd92297b Fix install guide 2025-06-10 02:11:13 +08:00
Jiang-Jia-Jun
00f08365a0 Merge pull request #2622 from PaddlePaddle/2.0.0-llm
[LLM] Upgrade FastDeploy to 2.0 version
2025-06-10 02:02:25 +08:00
jiangjiajun
1ebc4f9492 Update docker image address 2025-06-10 01:59:43 +08:00
jiangjiajun
f7cd5560fe Update README.md 2025-06-09 20:39:08 +08:00
jiangjiajun
0a42545723 [LLM] Add output module and polish docs 2025-06-09 20:30:41 +08:00
jiangjiajun
0d2651e594 [LLM] Add output module and polish docs 2025-06-09 20:29:17 +08:00
jiangjiajun
fb18f3092d [LLM] Add output module and polish docs 2025-06-09 20:26:53 +08:00
jiangjiajun
684703fd72 [LLM] First commit the llm deployment code 2025-06-09 19:20:15 +08:00
Jiang-Jia-Jun
980c0a1d2c Merge pull request #2592 from jules-ai/develop
fix Windows text encoding issue causing infinite loop
2025-02-24 10:00:36 +08:00
Jules
4f4f2e14bf fix Windows text encoding issue causing infinite loop 2025-02-14 18:40:00 +08:00
Jiang-Jia-Jun
eb141a09a0 Merge pull request #2548 from Zheng-Bicheng/develop
Update cosine_similarity.cc
2025-02-13 19:47:00 +08:00
Zheng-Bicheng
9faf1b5ad9 Merge branch 'PaddlePaddle:develop' into develop 2025-02-12 21:23:36 +08:00
Juncai
c521c6ae4c Merge pull request #2590 from kevincheng2/develop
update docs
2025-02-08 10:25:13 +08:00
kevin
47cddc5be3 update docs 2025-02-05 08:42:52 +00:00
Jiang-Jia-Jun
2dd9870b7d Merge pull request #2586 from jerrywgz/update_doc
update doc
2025-01-16 10:02:07 +08:00
wangguanzhong
907aff7934 update doc 2025-01-16 00:46:46 +08:00
Jiang-Jia-Jun
19e752c264 Merge pull request #2541 from Wanglongzhi2001/speculate_decoding
Support speculate decoding
2025-01-10 15:08:27 +08:00
Jiang-Jia-Jun
947f230612 Merge pull request #2542 from raoyutian/develop
Update README.md
2025-01-10 15:08:02 +08:00
Jiang-Jia-Jun
d4bbdbefea Merge pull request #2559 from MaaXYZ/fix/build_error
fix: build error without ENABLE_PADDLE2ONNX
2025-01-10 13:55:49 +08:00
Jiang-Jia-Jun
618826b39d Merge pull request #2560 from MaaXYZ/perf/read_file
perf: ReadBinaryFromFile supports Chinese path
2025-01-10 13:55:27 +08:00
Jiang-Jia-Jun
17d204b975 Merge pull request #2561 from MaaXYZ/feat/directml
feat: select adapter id for DirectML
2025-01-10 13:54:44 +08:00
Jiang-Jia-Jun
f968fdf512 Merge pull request #2564 from MaaXYZ/fix/config_including
fix: config including
2025-01-10 13:54:06 +08:00
Wanglongzhi2001
fe35dc5d77 update version of info_dict 2025-01-10 05:42:59 +00:00
Wanglongzhi2001
99d0921049 update 2025-01-09 07:33:42 +00:00
Wanglongzhi2001
ed5f65a694 fix typo 2025-01-09 07:33:42 +00:00
Wanglongzhi2001
5c42585c2a update 2025-01-09 07:33:42 +00:00
Wanglongzhi2001
ae57a2b068 fix typo 2025-01-09 07:33:42 +00:00
Wanglongzhi2001
934e8d846e update 2025-01-09 07:33:42 +00:00
Wanglongzhi2001
ce3c09d652 import proposer from nlp 2025-01-09 07:33:42 +00:00
Wanglongzhi2001
e3bc5aac37 fix typo 2025-01-09 07:33:42 +00:00
Wanglongzhi2001
08877a985d refactor code 2025-01-09 07:33:38 +00:00
Wanglongzhi2001
389015bf04 remove debug log 2025-01-09 07:32:44 +00:00
Wanglongzhi2001
d5b6499a94 remove debug log 2025-01-09 07:32:44 +00:00
Wanglongzhi2001
e52155f07e v1.0 align accuracy 2025-01-09 07:32:44 +00:00
Wanglongzhi2001
47aacb5062 add speculate_decoding framework 2025-01-09 07:32:41 +00:00
Jiang-Jia-Jun
97e541e70e Merge pull request #2584 from ming1753/internet
support return_all_tokens & stop_seqs
2025-01-08 19:22:45 +08:00
minghaipeng
c249b98aaa fix bug 2025-01-08 06:51:43 +00:00
minghaipeng
c7e1d58699 fix bug 2025-01-07 13:17:04 +00:00
minghaipeng
8266ed7ec7 fix bug 2025-01-07 12:32:11 +00:00
minghaipeng
093614e47d support stop_seqs 2025-01-07 06:35:25 +00:00
minghaipeng
cbd77205f3 make return_all_tokens work 2025-01-06 13:35:16 +00:00
minghaipeng
577b7a7681 support reduce_dialogue_repetition 2025-01-06 12:39:19 +00:00
MistEO
ec3d4c714c fix: valid_directml_backends 2024-11-21 16:47:16 +08:00
MistEO
11214a642f fix: typo of log 2024-11-21 16:11:31 +08:00
MistEO
227cc37a7b fix: config including 2024-11-21 16:02:19 +08:00
Juncai
608d4be580 Merge pull request #2563 from kevincheng2/develop
[llm] update docs
2024-11-21 15:50:37 +08:00