biondizzle 454dbdad52 P5: Fused mHC pre_block + RMSNorm + NVFP4 quantize kernel ...

- fused_mhc_rmsnorm_quantize.cu: 2-kernel approach
  Kernel 1: mhc_rmsnorm_amax_gsa — bmm + RMS + amax → gsa
  Kernel 2: mhc_rmsnorm_quantize_nvfp4 — bmm + normalize + quantize
- Python bridge: mhc_rmsnorm_quantize_nvfp4() in ops/quantize.py
- Unit test: test_fused_mhc_rmsnorm_quantize.py (production shapes)
- Eliminates ~610 kernel launches per token (122 sites × 5 launches saved)

2026-06-02 16:39:42 +00:00

..

attention

perf: skip MQA GQA expansion in FMHA (stride=0, no 128x K/V copy)

2026-06-02 03:54:03 +00:00

cache

fix: correct gather.py kernel_dir path

2026-05-30 21:12:09 +00:00

compressor

KV-1/KV-2/KV-3: NVFP4 compressed KV + FP8 indexer keys

2026-06-02 10:00:50 +00:00

cuda

P5: Fused mHC pre_block + RMSNorm + NVFP4 quantize kernel

2026-06-02 16:39:42 +00:00

gemm

fix: use cute.where() directly for clamp in fused SwiGLU

2026-06-02 08:16:41 +00:00

indexer

P0 COMPLETE: Eliminate ALL .item() CPU-GPU syncs from NVFP4 activation path

2026-06-01 21:05:03 +00:00

router

Switch router to Nvfp4Linear production GEMM (custom CuTeDSL kernel crashes MLIR)

2026-06-01 11:17:54 +00:00

__init__.py

Restructure: cutedsl/ -> dsv4/ with proper layering

2026-05-21 17:30:44 +00:00