Lianmin Zheng b01df48cf2 [Fix] Adjust default chunked prefill size and cuda graph max bs according to GPU memory capacity (#2044)

2024-11-15 06:21:57 -08:00

..

sglang

[Fix] Adjust default chunked prefill size and cuda graph max bs according to GPU memory capacity (#2044)

2024-11-15 06:21:57 -08:00

pyproject.toml

Fix outlines version (#2036)

2024-11-14 12:52:40 -08:00

upload_pypi.sh

Fix test cases (#6)

2024-01-15 01:15:53 -08:00