[Quantization] Auto-disable DeepGEMM for Kolibri 1 on SM12x (#61274)
Signed-off-by: Luca Motz <luca.motz@icloud.com> Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Opus 5.5
parent
3723a1ea96
commit
2d09fdcdc2
@@ -1547,8 +1547,6 @@ class VllmConfig:
|
||||
self.quant_config.use_deep_gemm = False
|
||||
logger.warning_once(
|
||||
"Auto-disabled DeepGemm for model_type=%s on Blackwell. "
|
||||
"DeepGemm E8M0 scale format causes accuracy degradation "
|
||||
"for this architecture. Falling back to CUTLASS. "
|
||||
"To disable DeepGemm globally, set VLLM_USE_DEEP_GEMM=0.",
|
||||
model_type,
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user