 Chunan ZengandKevin Mi
|
241a5b9823
|
MiniMax-M3: allow shared-experts fusion on ROCm gfx942 and newer (#36576)
Co-authored-by: Kevin Mi <kevin.mi@radixark.ai>
|
2026-09-16 19:55:47 -07:00 |
|
|
Chunan Zeng
|
d78b35076a
|
[CI] Fix missing elfutils headers in CUDA 13.4 DeepGEMM build (#39855)
|
2026-09-16 16:41:29 -07:00 |
|
|
Chunan ZengandKevin Mi
|
5177a3ec08
|
MiniMax-M3: Triton split-K router GEMV with in-kernel fixup (#36557)
Co-authored-by: Kevin Mi <45493463+kevin-mii@users.noreply.github.com>
|
2026-09-08 16:39:41 -07:00 |
|
|
Chunan ZengandKevin Mi
|
a25bbca8ed
|
MiniMax-M3: share the sparse index top-k across layers and reuse the decode top-k buffer (#36527)
Co-authored-by: Kevin Mi <mikevin920@yahoo.com>
|
2026-09-08 16:39:01 -07:00 |
|
|
Chunan Zeng
|
e226bb711c
|
enable TRT-LLM for MiniMax M3 by preserving SwiGLU params (#33962)
|
2026-08-09 23:30:05 -07:00 |
|
|
|
93173b27e8
|
integrate flash_mla_sparse_fwd (#25418)
Co-authored-by: Yuan Luo <yuan.luo@hotmail.com>
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
Co-authored-by: laixinn <q865809639@gmail.com>
Co-authored-by: MeowGrange <276466210+MeowGrange@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-06-03 01:09:25 -07:00 |
|
|
Chunan Zeng
|
e06058ed62
|
[Kernel] Import flash_mla kernels from sglang kernel for deepseek v4 (#26499)
|
2026-05-27 14:32:44 -07:00 |
|
|
Chunan Zeng
|
b66f8e0b96
|
Sgl flashmla (#26132)
|
2026-05-26 12:00:23 -07:00 |
|
|
Chunan Zeng
|
a7c3f74bec
|
[FA3 Feature] Support multi modal Llama-3.2-11B-Vision-Instruct (#5103)
|
2025-04-07 22:58:08 -07:00 |
|
|
Chunan Zeng
|
14269198e3
|
[Benchmark] tilelang vs deepgemm vs w8a8_block_fp8_matmul (#4735)
|
2025-03-24 20:56:31 -07:00 |
|
|
Chunan Zeng
|
65c24c28f9
|
[Quant Kernel] refactored per token group quant fp8 to support int8 up-to 2x faster (#4396)
|
2025-03-23 23:44:17 -07:00 |
|
|
Chunan Zeng
|
6a384d5c01
|
Speed up per token and per tensor quant by 15% (#4639)
|
2025-03-22 00:37:57 -07:00 |
|
|
Rex
|
07f944631e
|
Add awq dequantize kernel to sgl with 1x to 3x speedup (#4104)
|
2025-03-12 00:10:02 -07:00 |
|
|
Rex
|
90bb2be27e
|
Minor improvement to per_tensor_quant_fp8 (#4197)
|
2025-03-07 22:52:12 -08:00 |
|