biondizzle 014d647ba3 fix: sink bias domain correction — add attn_sink/scale to raw logits ...

The softmax scales by scale_log2 = scale * log2(e). Adding sink_val to
raw logits causes it to be scaled too. Fix: add sink_val/scale instead,
so after scaling: (sink_val/scale) * scale_log2 = sink_val * log2(e).
This correctly multiplies attention weights by exp(sink_val).

2026-05-26 15:03:49 +00:00

..

cache

Flush compressor: schema fix, prepare_forward, flush_write kernels, state rotation

2026-05-22 00:25:47 +00:00

kernels

fix: sink bias domain correction — add attn_sink/scale to raw logits

2026-05-26 15:03:49 +00:00

layers

NVFP4-1.1 integration: GPU-only quantize kernel + MoE pipeline wiring

2026-05-25 16:19:07 +00:00

loader

Restructure: cutedsl/ -> dsv4/ with proper layering

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

model

Fix layer construction: match existing API signatures, add RMSNorm impl

2026-05-21 23:31:58 +00:00

ops

NVFP4-3: add use_2cta_instrs conditional to gemm_runner

2026-05-25 16:42:02 +00:00

reference

Restructure: cutedsl/ -> dsv4/ with proper layering

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

__init__.py

Restructure: cutedsl/ -> dsv4/ with proper layering

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