 abing
|
fa826e08b1
|
Reuse shared compressed KV dequantization in DeepSeek V4.1 CP prefill
(cherry picked from commit 44eb378e94610e4ccc6b990bf09c105f8c8f9ee9)
|
2026-09-20 22:12:47 +08:00 |
|
|
abing
|
4f22146e51
|
Avoid host synchronization in DeepSeek V4.1 CP prefill
(cherry picked from commit 510596019fd5782d494c9b5227bf784d46661f6f)
|
2026-09-20 22:07:30 +08:00 |
|
|
abing
|
12e3b82e52
|
run pass cp+megamoe+bcg
(cherry picked from commit 85b8a150ef69c35cbd8c3fe940e41b414b903757)
|
2026-09-20 22:07:29 +08:00 |
|
|
abing
|
8305f66fc8
|
fix bug
(cherry picked from commit 60d31cb0c268c4b733ab290e133e3763b65f090e)
|
2026-09-20 22:07:24 +08:00 |
|
|
abing
|
21a4a16b4b
|
update code
(cherry picked from commit 1453150a0bdf2cce425e9e2da83ef16b8e8f2859)
|
2026-09-20 22:07:24 +08:00 |
|
|
abing
|
fc954b7e08
|
add test
(cherry picked from commit 094abd5e90af77507acd7c91513f69b5b29b685b)
|
2026-09-20 22:07:24 +08:00 |
|
|
abing
|
c2059c4fb2
|
run pass llm cp
(cherry picked from commit 1d85394563d96cf22d5d84f15c0e9043582419e4)
|
2026-09-20 22:07:23 +08:00 |
|
|
BingjiaWang
|
7782a2a1c8
|
[Benchmark] Limit warmup concurrency in serving benchmark (#39398)
|
2026-09-16 22:58:10 -07:00 |
|
|
BingjiaWang
|
861d40f3ee
|
Fix DSpark CUDA graph replay with MegaMoE TP attention (#34919)
|
2026-09-07 01:35:35 -07:00 |
|
|
BingjiaWang
|
3c481b9421
|
[Benchmark] Add optional steady-state window for serving metrics (#30918)
|
2026-08-24 14:49:20 -07:00 |
|
|
BingjiaWang
|
fd19a76237
|
[BUG] fix strip streaming empty-string suffix from DSV4 tool arguments (#29883)
|
2026-07-10 02:05:26 -07:00 |
|
|
BingjiaWang
|
ce7141ef98
|
add git gemm warpper for dispatch_bf16_fp32_backend (#25860)
|
2026-05-20 15:24:10 -07:00 |
|
|
BingjiaWangandabing
|
006bd44cf9
|
[deepseekv3.2] fix get_k_and_s_triton kenel for 128K seqlen case bug (#19319)
Co-authored-by: abing <wangbingjia.wbj@alibaba-inc.com>
|
2026-03-11 12:56:33 -07:00 |
|
|
BingjiaWangandabing
|
760ae933bb
|
optimize get_topk_ragged by fusing get k and k_scale triton kernel (#16043)
Co-authored-by: abing <wangbingjia.wbj@alibaba-inc.com>
|
2026-02-04 19:59:41 +08:00 |
|
|
BingjiaWang
|
612026ad2c
|
[OPT] DeepSeekV3.2: optimize indexer weight_proj-mma performance (#17205)
|
2026-01-20 23:09:44 +08:00 |
|