 Bruce-x-1997
|
793c96c3d2
|
[perf]optimize w4afp8 kernel on deepseek-v3-0324 (#12921)
Signed-off-by: bruce.xu <bruce.x@gmicloud.ai>
|
2025-12-18 18:13:22 +08:00 |
|
|
Bruce-x-1997
|
2e48584b62
|
[bugfix] set is_prefill_only=false when mixed_chunk (#10889)
|
2025-10-31 00:12:21 -07:00 |
|
|
Bruce-x-1997andforestlee95
|
21e1bc475c
|
[router] fix FunctionCallResponse proto, support arguments is null (#9875)
Co-authored-by: forestlee95 <forestlee95@foxmail.com>
|
2025-09-01 20:37:15 -07:00 |
|
|
Bruce-x-1997andbruce.xu
|
8b30bec265
|
[router] fix error response in pd_router (#9505)
Co-authored-by: bruce.xu <bruce.xu@gmicloud.ai>
|
2025-08-27 19:10:55 -07:00 |
|
|
Bruce-x-1997andbruce.xu
|
3aec3d4f8b
|
[Doc] add LWS(LeaderWorkerSet) use case in sgl-router README (#9568)
Co-authored-by: bruce.xu <bruce.xu@gmicloud.ai>
|
2025-08-25 08:32:31 -07:00 |
|
|
Bruce-x-1997andbruce.xu
|
9e169ea8b5
|
[router] add right rustls dependency in sgl-router cargo.toml (#9498)
Co-authored-by: bruce.xu <bruce.xu@gmicloud.ai>
|
2025-08-24 09:03:15 -07:00 |
|
|
Bruce-x-1997andbruce.xu
|
446c8e4cdb
|
[router] ignore client error when record failure in pd_router (#9503)
Co-authored-by: bruce.xu <bruce.xu@gmicloud.ai>
|
2025-08-22 14:19:45 -07:00 |
|