xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-07-23 02:47:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix][CI/CD][CPU] Fix CPU CI tests (#20383)

Browse Source 
Signed-off-by: jiang1.li <jiang1.li@intel.com>
This commit is contained in:
Li, Jiang 2025-07-03 11:11:36 +08:00 committed by GitHub
parent b616f6a53d
commit 0ec3779df7
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 7 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
vllm/model_executor/layers/quantization/utils/fp8_utils.py
View File

@ -201,12 +201,13 @@ def apply_w8a8_block_fp8_linear_fake(
return torch.empty(output_shape, dtype=input.dtype, device=input.device) return torch.empty(output_shape, dtype=input.dtype, device=input.device)
direct_register_custom_op( if not current_platform.is_cpu():
op_name="apply_w8a8_block_fp8_linear", direct_register_custom_op(
op_func=apply_w8a8_block_fp8_linear, op_name="apply_w8a8_block_fp8_linear",
mutates_args=[], op_func=apply_w8a8_block_fp8_linear,
fake_impl=apply_w8a8_block_fp8_linear_fake, mutates_args=[],
) fake_impl=apply_w8a8_block_fp8_linear_fake,
)
def input_to_float8( def input_to_float8(