18 Commits
Author SHA1 Message Date
Mohammad Miadh Angkad b7d8ceb444 [CI] Keep custom sgl-kernel wheel in CUDA CI (#24291) 2026-05-02 21:53:21 -07:00
Mohammad Miadh Angkad 90ef8ce54d [Docker] Remove flashinfer cache copy (#22653) 2026-04-13 09:48:22 -07:00
Mohammad Miadh Angkad 4dbd59850b Add bfloat16 KV cache validation for HiSparse (#22505) 2026-04-13 12:41:42 +08:00
Mohammad Miadh Angkad 701a0e0c25 [CI/Docker] Clean up redundant flashinfer cubin downloads (#22491) 2026-04-12 12:30:41 -07:00
Mohammad Miadh Angkad bcc0c65aa8 [DSA] Hopper FP8 FlashMLA KV padding (#22372) 2026-04-12 02:19:17 -07:00
Mohammad Miadh AngkadandDavid Wang c3833ba929 Enable DFLASH support for additional model backends (#22358)
Co-authored-by: David Wang <21328423+dcw02@users.noreply.github.com>
2026-04-09 14:36:12 -07:00
Mohammad Miadh Angkad b311db2e49 [Doc] Fix and improve DeepSeek V3.2/GLM-5 documentation (#22179) 2026-04-05 23:26:42 -07:00
Mohammad Miadh Angkad 088758c1c1 [Tiny] Improve docs (#17264) 2026-01-18 14:57:01 +08:00
Mohammad Miadh Angkad b0701f02b3 Fix benchmark import for should_use_tensor_core (#17232) 2026-01-16 17:48:36 -05:00
Mohammad Miadh Angkad c771933dc5 [Doc] Tiny docs update for CUDA 13 (#17200) 2026-01-16 20:53:36 +08:00
Mohammad Miadh Angkad ff97814232 Tiny fix hicache kernel backend comparison (#16867)
Signed-off-by: Mohammad Miadh Angkad <MAngkad.BSDSBA2027@aim.edu>
2026-01-10 18:10:42 -08:00
Mohammad Miadh Angkad 05ab110e02 [Performance] Force split_k=1 for MXFP4 Triton kernels on Hopper (#16014)
Signed-off-by: Mohammad Miadh Angkad <MAngkad.BSDSBA2027@aim.edu>
2026-01-08 23:52:22 +08:00
Mohammad Miadh Angkad 63b056213f Remove disused B300 Dockerfile (#13946) 2025-11-27 09:48:00 -05:00
Mohammad Miadh Angkad c7867b6702 [Fix] Add per_channel_quant parameter to MoE config functions (#11201) 2025-10-13 21:26:06 +08:00
Mohammad Miadh Angkad cd4da1f19b Refactor kv_cache_scheme handling for quantization (#10132) 2025-09-25 10:32:15 -07:00
Mohammad Miadh Angkad 321fecab74 Add sentencepiece to project dependencies (#10386) 2025-09-12 16:02:54 -07:00
Mohammad Miadh Angkad b9eb0d9c2b Change tensor alignment method to mn major (#9844) 2025-09-02 01:23:13 -07:00
Mohammad Miadh Angkad 70eedb58bb Fix typo in warning message about DeepGEMM JIT (#9802) 2025-08-30 03:35:53 -07:00