feat: add fast_decode_plan from flashinfer, flashinfer to 0.4.0rc3 (#10760)
Co-authored-by: Zihao Ye <yezihhhao@gmail.com> Co-authored-by: Sleepcoo <Sleepcoo@gmail.com>
This commit is contained in:
@@ -70,7 +70,7 @@ srt = [
|
||||
"torchaudio==2.8.0",
|
||||
"torchvision",
|
||||
"cuda-python",
|
||||
"flashinfer_python==0.4.0rc1",
|
||||
"flashinfer_python==0.4.0rc3",
|
||||
]
|
||||
|
||||
blackwell = [
|
||||
@@ -80,8 +80,8 @@ blackwell = [
|
||||
"torchaudio==2.8.0",
|
||||
"torchvision",
|
||||
"cuda-python",
|
||||
"flashinfer_python==0.4.0rc1",
|
||||
"nvidia-cutlass-dsl==4.2.1",
|
||||
"flashinfer_python==0.4.0rc3",
|
||||
"nvidia-cutlass-dsl==4.2.0",
|
||||
]
|
||||
|
||||
# HIP (Heterogeneous-computing Interface for Portability) for AMD
|
||||
|
||||
Reference in New Issue
Block a user