[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:
Luca Motz
2026-10-14 12:59:50 +00:00
committed by GitHub
co-authored by Claude Opus 5.5
parent 3723a1ea96
commit 2d09fdcdc2
3 changed files with 22 additions and 13 deletions
-2
View File
@@ -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,
)