biondizzle 36a6f07a7e Fix: unsqueeze k/v when dim==2

2026-05-27 06:52:43 +00:00

..

attention

Fix: unsqueeze k/v when dim==2

2026-05-27 06:52:43 +00:00

cache

…

compressor

…

cuda

fix quantize_nvfp4 kernel: use proven single-thread-per-CTA pattern from deinterleave_quantize.cu

2026-05-25 16:21:44 +00:00

decode

…

gemm

fix: add SwiGLU clamping to fused kernel (paper §4.2.3, CG-1)

2026-05-23 06:32:54 +00:00

indexer

Indexer: score+topk kernel, gather KV, compute_valid_lens

2026-05-22 01:20:39 +00:00

router

…

__init__.py

…