Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

444 #5

Closed
wants to merge 31 commits into from
Closed

444 #5

wants to merge 31 commits into from

Conversation

81549361
Copy link
Owner

Motivation

Modifications

Checklist

  • Format your code according to the Contributor Guide.
  • Add unit tests as outlined in the Contributor Guide.
  • Update documentation as needed, including docstrings or example tutorials.

Ying1123 and others added 30 commits September 9, 2024 13:05
@Ying1123
[CI] Return output logprobs in unit test (#1361)
689ff58
@hnyls2002
Unify forward mode (#1360)
69b3bb9
@zifeitong
Support OpenAI API json_schema response format (#1363)
9144ed1
@zhaochenyang20 @zhaochen20
Adding Documentation for installation (#1300)
743007e 
Co-authored-by: zhaochen20 <[email protected]>
@merrymercy
[Docs] Improve documentations (#1368)
8d1095d
@wcsjtu
[Fix] fix bug of undefined is_single in meth create_abort_task (#…
fec2d12 
…1370)
@Achazwl
Support MiniCPM3 (#1371)
e72275c
@josephrocca @zhyncs
Fix CORS compatibility with OpenAI, vLLM, TGI, LMDeploy (#1373)
dff2860 
Co-authored-by: Yineng Zhang <[email protected]>
@merrymercy
[Minor] improve kill scripts and torchao import (#1375)
6c7cb90
@hnyls2002
Fix vocab mask update bug (#1376)
fbb4754
@merrymercy
[Minor] move triton attention kernels into a separate folder (#1379)
3a6e8b6
@merrymercy
Deprecate --disable-flashinfer and introduce --attention-backend (#1380)
46094e0
@hnyls2002
Organize flashinfer indices update (#1378)
144bc70
@ByronHsu
remove assertion in triton attention and add an unit test (#1385)
8c0efa5
@blacker521
BaiChuan2 Model (#1367)
224200e 
Co-authored-by: wanpenghan <[email protected]>
@merrymercy
[Fix] Fix --disable-flashinfer (#1389)
15c75e4
@merrymercy
Improve error reporting during server launch (#1390)
c03cece
@merrymercy
Refactor attention backend (#1381)
fec185c
@hnyls2002
Add no commit to main rule (#1393)
4462137
@Achazwl
Fix README format (#1399)
2a71be5
@merrymercy
Support cuda graph in the triton attention backend (#1401)
3efa798
@yzh119
kernel: use tensor cores for flashinfer gqa kernels (#1403)
debbdb5
@kcz358
[Minor Fix] Fix llava modalities issue for single-image (#1402)
8234e66
@hxer7963 @merrymercy
Add Support for XVERSE Models (Dense and MoE) to sglang (#1397)
c33d82a 
Co-authored-by: will he <[email protected]>
Co-authored-by: root <[email protected]>
Co-authored-by: Lianmin Zheng <[email protected]>
@Ying1123
[Feature] Initial support for multi-LoRA serving (#1307)
7122169
@Ying1123
[Minor, CI] remove lora test from minimal suite (#1406)
eb02c16
@merrymercy
Make stop reason a dict instead of str (#1407)
b912de1
@merrymercy
[CI] Include triton backend and online serving benchmark into CI (#1408)
68be2f6
@Ying1123
[Minor] Raise exception for wrong import (#1409)
9a903a8
@merrymercy
Balance test in CI (#1411)
ad0ff62
@81549361 81549361 closed this Sep 13, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.