lukecandyinfan98 a53fe428f9 Support FlashMLA backend (#4472) ...

Co-authored-by: yinfan98 <1106310035@qq.com>

2025-03-16 09:07:06 -07:00

..

deprecated

Move sgl.Runtime under sglang/lang (#2990)

2025-01-19 17:10:29 -08:00

playground

Support FlashMLA backend (#4472)

2025-03-16 09:07:06 -07:00

ci_install_dependency.sh

[Eagle] Remove the greedy branch and some redundant code (#4363)

2025-03-16 02:48:55 -07:00

ci_install_rust.sh

[router] Allow empty worker list for sglang.launch_router (#2979)

2025-01-19 01:05:23 -08:00

export_deepseek_nextn.py

Share target model embed and head weights for nextn (#4033)

2025-03-03 13:30:04 -08:00

fix_corrupted_json.py

[Profile] Add pytorch profiler (#1604)

2024-10-07 14:37:16 -07:00

killall_sglang.sh

Support penalty in overlap mode; return logprob with chunked prefill; improve benchmark scripts (#3988)

2025-03-03 00:12:04 -08:00

update_kernel_whl_index.py

Update whl index path (#3128)

2025-01-25 23:57:09 +08:00

version_branch_to_tag.sh

CI: Update scripts to fail fast (#2672)

2024-12-30 19:04:01 -08:00