Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
Menu
Open sidebar
OpenDAS
vllm_cscc
Commits
4f359a911580cfac6da55e2f840d8264d4fa3231
Switch branch/tag
vllm_cscc
vllm
zero_overhead
18 Aug, 2025
4 commits
fix issue from merge
· 4f359a91
zhuwenwen
authored
Aug 18, 2025
4f359a91
debug and fix erro
· e70b0ea0
zhuwenwen
authored
Aug 18, 2025
e70b0ea0
fix mtp accept rate issu
· 1555157e
zhuwenwen
authored
Aug 18, 2025
1555157e
add v1 engine + deepseek r1 mtp + zero-overhead scheduler
· 22a95571
zhuwenwen
authored
Aug 18, 2025
22a95571
13 Aug, 2025
1 commit
add v1 engine zero overhead
· 295dfac8
zhuwenwen
authored
Aug 13, 2025
295dfac8
31 Jul, 2025
1 commit
remove unused code
· 1b78ef29
zhuwenwen
authored
Jul 31, 2025
1b78ef29
10 Jul, 2025
1 commit
fix zero overhead to support chunk prefill
· a495fc3b
zhuwenwen
authored
Jul 10, 2025
a495fc3b
26 May, 2025
1 commit
Update sequence.py fix assert error。
· d82fa156
lizhg1
authored
May 26, 2025
d82fa156
23 May, 2025
1 commit
tbo增加ds int8支持,修改tb zerooverhead环境变量到envs.py中统一管理
· dbbb148b
lizhigong
authored
May 23, 2025
dbbb148b
16 May, 2025
1 commit
修复zero-overhead首字正确性问题,zero-overhead不使用默认流调整,增加two-batch-overlap功能
· 2a935929
lizhigong
authored
May 16, 2025
2a935929
09 May, 2025
11 commits
debug on v0.8.5
· cf1d8464
lizhigong
authored
May 09, 2025
cf1d8464
pause speculative decoding with zero overhead scheduling, develop tbo first
· 0ee425a6
lizhigong
authored
May 08, 2025
0ee425a6
rm debug log
· 7d224eb2
lizhigong
authored
May 08, 2025
7d224eb2
debug spec decode zero overhead
· 0ecda6d1
lizhigong
authored
May 08, 2025
0ecda6d1
add spec decode zero overhead
· 01c30741
lizhigong
authored
Apr 27, 2025
01c30741
delete triton kernel ,use tensor indices
· b01c8270
lizhigong
authored
Apr 27, 2025
b01c8270
fix zero scheduler on v0.8.4
· 1ed30424
lizhigong
authored
Apr 27, 2025
1ed30424
fix stop remote worker bug
· 351d607d
lizhigong
authored
Apr 27, 2025
351d607d
add VLLM_ZERO_DISABLE_AUTO_THREAD VLLM_ZERO_NO_THREAD change zero scheduling logic
· 9076ef2b
lizhigong
authored
Apr 15, 2025
9076ef2b
debug v0 zero overhead schedule
· 4ff58b66
lizhigong
authored
Apr 14, 2025
4ff58b66
add v0 zero overhead
· 54294854
lizhigong
authored
Apr 11, 2025
54294854