COMMITS
March 11, 2025
V
[hotfix] Update server script
Vikranth Srivatsa committed
V
Merge pull request #81 from WukLab/bugfix/fix_vllm_tensor_parallel
Vikranth Srivatsa committed
V
Fix tensor parallel vllm initialization
Vikranth Srivatsa committed
March 4, 2025
V
Update server.py to expose start_server
Vikranth Srivatsa committed
July 28, 2024
V
Update README.md with arxiv url
Vikranth Srivatsa committed
May 24, 2024
V
Update README.md with preprint url
Vikranth Srivatsa committed
V
Update README.md with test pypi instructions
Vikranth Srivatsa committed
V
Merge pull request #72 from WukLab/feature/basic_server
Vikranth Srivatsa committed
V
Update python packge to be under preble for open source release
vikranth22446 committed
V
Update server configuration with better cli arguments
vikranth22446 committed
V
Add a basic Python Server Impl with url runtime + round robin
vikranth22446 committed
V
Merge pull request #71 from WukLab/perf/improve_global_scheduler_with_counter_perf
Vikranth Srivatsa committed
May 23, 2024
V
Fix Rebalancer for VE and zipf integration with Infercept
vikranth22446 committed
V
Add virtualenv exp utils
vikranth22446 committed
V
Update virtualenv experiment setup
vikranth22446 committed
May 22, 2024
V
Update global scheduler
vikranth22446 committed
May 18, 2024
Z
Merge pull request #70 from WukLab/refactor/rebase
Zijian committed
J
tried on video dataset after merge
jiange91 committed
May 17, 2024
J
check small example result after merge
jiange91 committed
May 16, 2024
J
merge from upstream
jiange91 committed
May 15, 2024
V
Merge pull request #69 from WukLab/ckpt/videoQA
Vikranth Srivatsa committed
V
Add perf global scheduling
vikranth22446 committed
V
Remove unneeded files
vikranth22446 committed
V
Fix global scheduler for loogle
vikranth22446 committed
May 14, 2024
L
Format code (#441)
Liangsheng Yin committed
K
[Feat] Add llava qwen, llava mistral (#419)
Kaichen Zhang - NTU committed
L
Update version to 0.1.16 (#438)
Lianmin Zheng committed
L
Fix streaming (#437)
Lianmin Zheng committed
May 13, 2024
Y
support llava video (#426)
Yuanhan Zhang committed
L
Handle truncation errors (#436)
Lianmin Zheng committed