vllm-project/vllm
1
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2025-12-06 06:53:12 +08:00
Code Issues Packages Projects Releases Wiki Activity
11,993 Commits 170 Branches 98 Tags

Default Branch

main

7b5575fa7d · [Bug] Fix vLLM config is not set error (#29999) · Updated 2025-12-06 05:42:12 +08:00
 ZIP  TAR.GZ

Branches

wentao-optimize-group-topk

bb310e3689 · reduce code · Updated 2025-12-06 06:41:42 +08:00
0
5
 ZIP  TAR.GZ
wentao-fix-torch-warning

5bc9eaf6db · default not change · Updated 2025-12-06 06:35:30 +08:00
0
7
 ZIP  TAR.GZ
wentao-optimize-startup-logs-4

6add39d6f9 · Merge branch 'main' into wentao-optimize-startup-logs-4 · Updated 2025-12-06 06:08:34 +08:00
0
6
 ZIP  TAR.GZ
khluu/refactor_ci

89a0c2918a · run all patterns · Updated 2025-12-05 19:34:57 +08:00
166
25
 ZIP  TAR.GZ
model-bash-tools

aa504ef728 · updated · Updated 2025-12-05 05:52:00 +08:00
43
7
 ZIP  TAR.GZ
wentao-deepgemm-fused-layout-kernel

b3deaff9af · Merge branch 'main' into wentao-deepgemm-fused-layout-kernel · Updated 2025-12-05 01:40:18 +08:00
56
6
 ZIP  TAR.GZ
revert-29385-eplb_nightly_ci

050af1adf6 · Revert "[CI] Add Async Eplb nightly CI tests (#29385)" · Updated 2025-12-05 00:50:37 +08:00
52
1
 ZIP  TAR.GZ
test-docker-cache

f500b65290 · Update async_llm_streaming.py · Updated 2025-12-04 07:08:42 +08:00
86
1
 ZIP  TAR.GZ
wentao-enable-cudagraph-for-deepepHT

41ffce7282 · address comments · Updated 2025-12-04 06:21:41 +08:00
97
7
 ZIP  TAR.GZ
releases/v0.12.0

4fd9d6a85c · [Core] Rename PassConfig flags as per RFC #27995 (#29646) · Updated 2025-12-03 12:38:43 +08:00
144
12
 ZIP  TAR.GZ
batched_triton_fallback

53fa4c6ad2 · Disabled DeepGEMM -> batched triton fallback by default · Updated 2025-12-03 04:52:48 +08:00
130
1
 ZIP  TAR.GZ
zhuohan/remove-redundant-argument

aac6674f78 · [Misc] Remove redundant engine arg tokens_only · Updated 2025-12-02 09:28:00 +08:00
165
1
 ZIP  TAR.GZ
wentao-TritonMLA-support-without-prefix-caching

9ecc612098 · Merge branch 'main' into wentao-TritonMLA-support-without-prefix-caching · Updated 2025-12-02 06:34:54 +08:00
167
15
 ZIP  TAR.GZ
wentao-fix-python-install-ci-error

451959c6cc · fix python install ci error · Updated 2025-12-02 06:19:43 +08:00
167
1
 ZIP  TAR.GZ
copilot/disable-batched-triton-kernel

320e717c80 · Merge branch 'main' into copilot/disable-batched-triton-kernel · Updated 2025-12-01 23:59:27 +08:00
176
7
 ZIP  TAR.GZ
woosuk/v2-penalties

99e0359065 · minor · Updated 2025-11-29 03:55:14 +08:00
264
5
 ZIP  TAR.GZ
deepseek_optimizations_alex_rob

ba25edb264 · add file · Updated 2025-11-26 21:56:58 +08:00
500
5
 ZIP  TAR.GZ
khluu/test_pull_through_cache

3137991f55 · [BugFix] EPLB + B200 + DeepGEMM : Handle column-major scales tensor (#29162) · Updated 2025-11-22 06:28:17 +08:00
451
0
 Included
 ZIP  TAR.GZ
andy-neuma-testing

1840c5cb18 · [BugFix] Make sure to allocate worst case MoE workspace during profile run in the DP + EP case (#27426) · Updated 2025-11-22 03:41:52 +08:00
455
0
 Included
 ZIP  TAR.GZ
skip-lmfe-tests

bf316c2650 · [CI] Skip lm-format-enforcer test cases · Updated 2025-11-21 03:40:33 +08:00
506
1
 ZIP  TAR.GZ