Yongye ZhuandClaude Opus 5.5 a6009ea85b [Kernel][Build] Bump DeepGEMM to the 26/09/30 release and adapt the sparse indexer (#61149) ...

Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

2026-10-12 23:24:43 -07:00

..

__init__.py

[4/N][warmup][DSv4] Migrate common attention kernels (#50176)

2026-09-08 10:25:48 -04:00

cache_utils.py

[Perf][DSv4] Fuse inverse RoPE + FP8 quant into FlashInfer sparse MLA (#58621)

2026-09-24 23:26:50 -07:00

fused_compress_quant_cache.py

[Kernel][Build] Bump DeepGEMM to the 26/09/30 release and adapt the sparse indexer (#61149)

2026-10-12 23:24:43 -07:00

fused_indexer_q.py

[Bugfix][Kernel] Restore FP fusion for indexer Q quantization (#60716)

2026-10-09 09:46:41 +00:00

fused_inv_rope_fp8_quant.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

fused_mtp_input_rmsnorm.py

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

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

save_partial_states.py

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

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