biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Bugfix][ROCm] Fix typo: is_linear_fp8_enaled -> is_linear_fp8_enabled (#31109)

Browse Source 
Signed-off-by: c0de128 <kevin.mckay@outlook.com>
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
This commit is contained in:
Kevin McKay
2025-12-21 23:14:58 -06:00
committed by GitHub
parent 44ae85f725
commit cf8eed7bef
5 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/layers/quantization/fp8.py
View File

@@ -414,7 +414,7 @@ class Fp8LinearMethod(LinearMethodBase):
if vllm_is_batch_invariant():
self.use_marlin = False
self.use_aiter_and_is_supported = rocm_aiter_ops.is_linear_fp8_enaled()
self.use_aiter_and_is_supported = rocm_aiter_ops.is_linear_fp8_enabled()
self.use_deep_gemm = is_deep_gemm_supported()
self.weight_block_size = self.quant_config.weight_block_size