Optimized deepseek-v3/r1 model performance on mxfp4 run (#9671)

Co-authored-by: wunhuang <wunhuang@amd.com> Co-authored-by: wghuang <wghuang@amd.com>
2025-09-02 22:26:28 -07:00
parent bcbeed714f
commit 0dfd54d11d
7 changed files with 455 additions and 59 deletions
@@ -0,0 +1,13 @@
+from aiter.ops.triton.batched_gemm_afp4wfp4_pre_quant import (
+    batched_gemm_afp4wfp4_pre_quant,
+)
+from aiter.ops.triton.fused_mxfp4_quant import (
+    fused_flatten_mxfp4_quant,
+    fused_rms_mxfp4_quant,
+)
+
+__all__ = [
+    "fused_rms_mxfp4_quant",
+    "fused_flatten_mxfp4_quant",
+    "batched_gemm_afp4wfp4_pre_quant",
+]