biondizzle 5290c91c35 fix quantize_nvfp4 kernel: use proven single-thread-per-CTA pattern from deinterleave_quantize.cu ...

The warp shuffle approach failed because __shfl_down_sync with 16 threads
has undefined behavior for the odd nibble. Use the same pattern as the
working deinterleave_quantize.cu: 1 CTA per 16-element block, 16 threads
per CTA, each thread reads all 16 elements sequentially and computes
amax + quantize + pack.

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

..

__init__.py

Restructure: cutedsl/ -> dsv4/ with proper layering

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

_hash_router.py

Router: full kernel stack — hash, topk, activation+topk, dense decode/prefill

2026-05-21 21:54:05 +00:00

activation_topk.cu

Router: full kernel stack — hash, topk, activation+topk, dense decode/prefill

2026-05-21 21:54:05 +00:00

append_swa.cu

KV Cache: schema, allocator, pools, manager, append_swa kernel

2026-05-22 00:08:38 +00:00

deinterleave_quantize.cu

Restructure: cutedsl/ -> dsv4/ with proper layering

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

flush_write.cu

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

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

gather_kv.cu

Indexer: score+topk kernel, gather KV, compute_valid_lens

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

hash_router.cu

Router: full kernel stack — hash, topk, activation+topk, dense decode/prefill

2026-05-21 21:54:05 +00:00

indexer_score_topk.cu

Fix indexer score kernel: use static shared memory, correct FP4 head offsets

2026-05-22 01:45:05 +00:00

quantize_nvfp4.cu

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

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

sparse_topk_metadata.cu

Restructure: cutedsl/ -> dsv4/ with proper layering

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

topk_select.cu

Router: full kernel stack — hash, topk, activation+topk, dense decode/prefill

2026-05-21 21:54:05 +00:00