[Bugfix] Restrict FlashInfer cuDNN FP8 ViT attention gate to Blackwell (SM 100) (#45251)
Signed-off-by: Wentian Byte <3400259131@qq.com>
This commit is contained in:
@@ -396,8 +396,9 @@ class MMEncoderAttention(CustomOp):
|
||||
if not is_flashinfer_cudnn_fp8_prefill_attn_supported():
|
||||
raise ValueError(
|
||||
"mm_encoder_attn_dtype='fp8' requires the FlashInfer "
|
||||
"cuDNN backend with cuDNN >= 9.17.1 on a GPU with native "
|
||||
"FP8 support."
|
||||
"cuDNN backend with cuDNN >= 9.17.1 on Blackwell (SM 100) "
|
||||
"or newer. cuDNN's FP8 SDPA path with bf16/fp16 output is "
|
||||
"not available on Hopper (H100/H200) or earlier."
|
||||
)
|
||||
|
||||
self.fp8_enabled = True
|
||||
|
||||
Reference in New Issue
Block a user