Unverified Commit 05977923 authored by Frank Wang's avatar Frank Wang Committed by GitHub
Browse files

[Minor] Add logging when using MXFP4 MXFP8 TRTLLM backend (#34916)


Signed-off-by: default avatarfrankwang28 <frank.wbb@hotmail.com>
Signed-off-by: default avatarFrank Wang <41319051+frankwang28@users.noreply.github.com>
Co-authored-by: default avatarWentao Ye <44945378+yewentao256@users.noreply.github.com>
parent ea37530b
...@@ -128,6 +128,9 @@ def get_mxfp4_backend(with_lora_support: bool) -> Mxfp4Backend: ...@@ -128,6 +128,9 @@ def get_mxfp4_backend(with_lora_support: bool) -> Mxfp4Backend:
and has_flashinfer() and has_flashinfer()
and envs.VLLM_USE_FLASHINFER_MOE_MXFP4_MXFP8 and envs.VLLM_USE_FLASHINFER_MOE_MXFP4_MXFP8
): ):
logger.info_once(
"Using FlashInfer MXFP4 MXFP8 TRTLLM backend for SM100", scope="local"
)
return Mxfp4Backend.SM100_FI_MXFP4_MXFP8_TRTLLM return Mxfp4Backend.SM100_FI_MXFP4_MXFP8_TRTLLM
elif current_platform.is_device_capability_family(100) and has_flashinfer(): elif current_platform.is_device_capability_family(100) and has_flashinfer():
logger.info_once( logger.info_once(
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment