xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-24 03:55:02 +08:00
Code Issues Packages Projects Releases Wiki Activity

[CI/Test] Fix FP8 per-tensor quant test reference scale shape (#30352)

Browse Source 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
This commit is contained in:
Lucas Wilkinson 2025-12-09 13:52:20 -05:00 committed by GitHub
parent 95501a70ec
commit b37bf51e75
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
tests/kernels/quant_utils.py
View File

@ -103,7 +103,7 @@ def ref_dynamic_per_tensor_fp8_quant(
.clamp(fp8_traits_min, fp8_traits_max) .clamp(fp8_traits_min, fp8_traits_max)
.to(FP8_DTYPE) .to(FP8_DTYPE)
) )
return ref_out, ref_scale.view((1, 1)) return ref_out, ref_scale.view(1)
def native_w8a8_block_matmul( def native_w8a8_block_matmul(