vllm.models.mistral.nvidia.ops
¶
Hand-fused eager kernels for Mistral models.
VLLM_ML4_FUSIONS selects them: a comma-separated subset of
:data:FUSIONS, all (default) or none.
Modules:
-
indexer–DSA indexer Q/K epilogues.
-
layernorm–One-launch LayerNorm: fp32 statistics and affine, output in the input dtype.
-
ssmax–SSMax query scaling
q *= s * log(pos + 1) + b, alone or fused with RoPE.