biondizzle b32713c302 grouped_linear: Pre-allocate output buffer for grouped GEMM (CUDA graph capture) ...

Add _output_buf_padded for the flat GEMM output, pass as out= parameter
to run_nvfp4_grouped_gemm to avoid per-step torch.zeros() allocation.

2026-06-03 22:02:01 +00:00

..

_archive

Cleanup Step 2: Archive Lineage P code, fix broken imports

2026-06-02 19:27:07 +00:00

cache

Cleanup Step 2: Archive Lineage P code, fix broken imports

2026-06-02 19:27:07 +00:00

decode

CUDA graph: Fix remaining sync violations from B200 detector run 2

2026-06-03 17:20:34 +00:00

kernels

Fix compressor: do not add positional bias to KV content

2026-06-03 15:52:00 +00:00

layers

grouped_linear: Pre-allocate output buffer for grouped GEMM (CUDA graph capture)

2026-06-03 22:02:01 +00:00

loader

Cleanup Step 2: Archive Lineage P code, fix broken imports

2026-06-02 19:27:07 +00:00

model

Cleanup Step 2: Archive Lineage P code, fix broken imports

2026-06-02 19:27:07 +00:00

ops

Fix: Add out= parameter to run_fused_swiglu_grouped_gemm signature

2026-06-03 21:45:15 +00:00

reference

Cleanup Step 2: Archive Lineage P code, fix broken imports

2026-06-02 19:27:07 +00:00

__init__.py

Restructure: cutedsl/ -> dsv4/ with proper layering

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