[MLA Attention Backend] Add TOKENSPEED_MLA backend for DSR1/Kimi K25 prefill + decode on Blackwell (#41778)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com> Signed-off-by: Roger Wang <hey@rogerw.io> Co-authored-by: Roger Wang <hey@rogerw.io>
This commit is contained in:
@@ -1362,6 +1362,7 @@ def backend_supports_prefill_query_quantization() -> bool:
|
||||
return backend_cls.get_name() in (
|
||||
"FLASHINFER",
|
||||
"TRTLLM_RAGGED",
|
||||
"TOKENSPEED_MLA",
|
||||
)
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user