[NVIDIA] Add SM100 Flashinfer MoE per tensor scale fp8 backend (#21458)
Signed-off-by: Amir Klein <203507526+amirkl94@users.noreply.github.com> Signed-off-by: mgoin <mgoin64@gmail.com> Co-authored-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
@@ -66,6 +66,8 @@ def _lazy_import_wrapper(module_name: str,
|
||||
# Create lazy wrappers for each function
|
||||
flashinfer_trtllm_fp8_block_scale_moe = _lazy_import_wrapper(
|
||||
"flashinfer.fused_moe", "trtllm_fp8_block_scale_moe")
|
||||
flashinfer_trtllm_fp8_per_tensor_scale_moe = _lazy_import_wrapper(
|
||||
"flashinfer.fused_moe", "trtllm_fp8_per_tensor_scale_moe")
|
||||
flashinfer_cutlass_fused_moe = _lazy_import_wrapper("flashinfer.fused_moe",
|
||||
"cutlass_fused_moe")
|
||||
fp4_quantize = _lazy_import_wrapper("flashinfer", "fp4_quantize")
|
||||
|
||||
Reference in New Issue
Block a user