Woosuk KwonandCodex 50d812b66a [Perf][DSV4.1] Optimize MegaMoE staging and NVFP4 cache gathers (#57604) ...

Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Codex <noreply@openai.com>

2026-09-18 12:57:19 -07:00

..

__init__.py

Fix early CUDA init (#43791)

2026-05-27 09:30:11 -07:00

dequant_gather_k_cutedsl.py

[Model][DSv4.1] Store the whole KV in MXFP8 (FlashMLA V4.1 record) (#56893)

2026-09-14 20:12:55 -07:00

fused_indexer_q_cutedsl.py

[DSA] Wire DeepGEMM sparse MQA logits into the DeepSeek V4.1 indexer (#56254)

2026-09-15 14:07:14 -07:00

o_proj.py

[Model] DeepSeek-V4.1-Flash Model Definitions (#56228)

2026-09-10 20:16:26 +08:00

prepare_megamoe.py

[Perf][DSV4.1] Optimize MegaMoE staging and NVFP4 cache gathers (#57604)

2026-09-18 12:57:19 -07:00

sparse_attn_compress_cutedsl.py

[5/N][warmup][DSv4] Migrate NVIDIA CuTeDSL attention kernels (#53566)

2026-09-12 00:05:59 -04:00