Lianmin Zheng 665815969a Enable cuda graph by default (#612)

2024-07-13 05:29:46 -07:00

..

backend

[Feat] Expose logprob options to sgl.gen API (#503)

2024-07-09 00:35:39 -07:00

lang

[Feat] Expose logprob options to sgl.gen API (#503)

2024-07-09 00:35:39 -07:00

srt

Enable cuda graph by default (#612)

2024-07-13 05:29:46 -07:00

test

Higher priority for user input of max_prefill_tokens & format (#540)

2024-06-12 21:48:40 -07:00

__init__.py

bump version to 0.1.19

2024-07-09 02:23:14 -07:00

api.py

[Feat] Expose logprob options to sgl.gen API (#503)

2024-07-09 00:35:39 -07:00

bench_latency.py

Enable cuda graph by default (#612)

2024-07-13 05:29:46 -07:00

global_config.py

Enable cuda graph by default (#612)

2024-07-13 05:29:46 -07:00

launch_server_llavavid.py

Minor fix in compiler & format (#545)

2024-06-29 23:42:14 -07:00

launch_server.py

Multi-node Tensor Parallelism (#550)

2024-06-17 20:41:24 -07:00

utils.py

Higher priority for user input of max_prefill_tokens & format (#540)

2024-06-12 21:48:40 -07:00