 Ke Bao
|
8b1942c6cc
|
Remove type conversion and fix id map in topk (#7759)
|
2025-07-03 18:13:32 -07:00 |
|
|
Ke Bao
|
00aec6ad6c
|
Apply dsv3_fused_a_gemm kernel (#7635)
|
2025-07-01 22:32:05 -07:00 |
|
|
Ke Bao
|
04b35190e2
|
Add dsv3 fused a gemm to sgl-kernel (#7630)
|
2025-06-29 02:52:24 -07:00 |
|
|
Ke Bao
|
57ab776910
|
Fuse sorted_token_ids padding to moe_align_block_size kernel (#7437)
|
2025-06-24 17:44:27 -07:00 |
|
|
Ke Bao
|
7151194bb2
|
Remove cumsum_buffer initilization (#7439)
|
2025-06-24 02:22:16 -07:00 |
|
|
Ke Bao
|
50f1b6d6b1
|
Remove copy after bmm (#7441)
|
2025-06-22 15:07:44 -07:00 |
|
|
Ke Bao
|
cc74499d51
|
Fix draft extend ut stability with flush cache (#6979)
|
2025-06-08 17:09:32 -07:00 |
|
|
Ke Bao
|
a2cb5913a0
|
Add draft extend CUDA graph for flashinfer backend (#6805)
|
2025-06-02 01:51:26 -07:00 |
|
|
Ke Bao
|
7e41290082
|
Add draft extend CUDA graph for Triton backend (#6705)
|
2025-05-29 00:13:07 -07:00 |
|
|
Ke Bao
|
f127355a30
|
Add batch test for draft extend (#6672)
|
2025-05-27 16:32:05 -07:00 |
|
|
Ke BaoandSehoon Kim
|
631950280a
|
Support EAGLE draft extend CUDA graph (#6606)
Co-authored-by: Sehoon Kim <sehoonkim@berkeley.edu>
|
2025-05-27 02:35:17 -07:00 |
|
|
Ke Baoandmerrymercy
|
6ce0ed073b
|
Apply constraint grammar to EAGLE (#6499)
Co-authored-by: merrymercy <lianminzheng@gmail.com>
|
2025-05-21 17:18:41 -07:00 |
|
|
Ke Bao
|
d8ab60117f
|
Overlap qk norm with two streams (#5977)
|
2025-05-02 09:26:30 -07:00 |
|
|
Ke Bao
|
6579cd7daf
|
Fix set kv cache multi-stream (#5975)
|
2025-05-02 09:26:00 -07:00 |
|
|
Ke Bao
|
ebaba85655
|
Update ci test and doc for MTP api change (#5952)
|
2025-05-01 09:30:27 -07:00 |
|
|
Ke Bao
|
de2faef97e
|
Remove extra contiguous (#5953)
|
2025-05-01 09:28:46 -07:00 |
|
|
Ke Bao
|
dd408ee481
|
Auto set draft model path for MTP (#5793)
|
2025-04-29 16:25:40 -07:00 |
|
|
Ke Bao
|
799c4bb502
|
Fuse MLA set kv cache kernel (#5748)
|
2025-04-26 18:42:22 -07:00 |
|
|
Ke Bao
|
c3948ba67e
|
Reorder loop in shared expert weight loading (#5719)
|
2025-04-25 17:27:42 -07:00 |
|
|
Ke Bao
|
6b6e748775
|
Remove q concat in FA3 backend for DeepSeek decode (#5638)
|
2025-04-22 11:43:12 -07:00 |
|
|
Ke Baoandsaienduri
|
11b23ae97b
|
Remove extra copy in deepseek forward absorb (#5578)
Co-authored-by: saienduri <saimanas.enduri@amd.com>
|
2025-04-21 19:33:21 -07:00 |
|
|
Ke BaoandYineng Zhang
|
5e0a9b0981
|
Apply deepseek cuda rope (#5385)
Co-authored-by: Yineng Zhang <me@zhyncs.com>
|
2025-04-14 15:22:43 -07:00 |
|
|
Ke Bao
|
5ad0571903
|
Adjust ci test threshold (#5271)
|
2025-04-11 22:03:37 -07:00 |
|
|
Ke Bao
|
1078396f47
|
Update deps for mllama4 (#5215)
|
2025-04-10 09:12:44 -07:00 |
|
|
Ke BaoandCheng Wan
|
ade714a67f
|
Add Llama4 user guide (#5133)
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
|
2025-04-07 19:09:34 -07:00 |
|
|
Ke Bao
|
aa08aeacf4
|
update torch compile doc (#4874)
|
2025-03-28 19:49:30 -07:00 |
|
|
Ke Bao
|
b39532587b
|
Update doc for DeepSeek-V3-0324 (#4825)
|
2025-03-27 13:30:40 -07:00 |
|
|
Ke Bao
|
77cf771ebe
|
Fix EAGLE3 for llama3.3 70b (#4716)
|
2025-03-24 17:31:19 -07:00 |
|
|
Ke Baoandchromecast56
|
8f163b1653
|
Add EAGLE mtbench benchmark script (#4676)
Co-authored-by: chromecast56 <jamesll@mit.edu>
|
2025-03-22 13:34:01 -07:00 |
|
|
Ke Bao
|
bfb03c6182
|
Update doc for MTP and DP attention (#4622)
|
2025-03-20 11:31:48 -07:00 |
|
|
Ke Bao
|
45212ce18b
|
Add deepseek v2 torch compile pr test (#4538)
|
2025-03-18 00:29:24 -07:00 |
|
|
Ke Bao
|
3ded4b215d
|
Revert "feat: update grouped_topk to support softmax and sigmoid" (#4505)
|
2025-03-17 11:30:26 -07:00 |
|
|
Ke Bao
|
3a08f54638
|
Update MTP doc (#4290)
|
2025-03-11 00:46:55 -07:00 |
|
|
Ke Bao
|
f1d09a6541
|
Update bench speculative script (#4235)
|
2025-03-09 12:19:01 -07:00 |
|
|
Ke Bao
|
20c8119915
|
Fix eagle hang issue for max_new_tokens=1 (#4185)
|
2025-03-07 12:11:18 -08:00 |
|
|
Ke Bao
|
ef9d3b3c2c
|
Fix triton kernel illegal memory issue for eagle (#4100)
|
2025-03-05 11:23:53 -08:00 |
|
|
Ke Bao
|
03b0364f76
|
Update nextn ci test (#4071)
|
2025-03-04 13:01:24 -08:00 |
|
|
Ke Bao
|
9fafa62db7
|
Share target model embed and head weights for nextn (#4033)
|
2025-03-03 13:30:04 -08:00 |
|
|
Ke Bao
|
d3fe9bae56
|
Add accuracy test for TP torch compile (#3994)
|
2025-03-02 13:18:18 -08:00 |
|
|
Ke Baoandyizhang2077
|
00ce7e311c
|
Fix all gather torch compile (#3992)
Co-authored-by: yizhang2077 <1109276519@qq.com>
|
2025-03-02 00:41:38 -08:00 |
|
|
Ke Bao
|
ddcf9fe3be
|
Optimize triton attention custom mask (#3731)
|
2025-02-21 00:54:41 +08:00 |
|
|
Ke Bao
|
e5ce395a6c
|
Fix draft decode max batch size (#3676)
|
2025-02-18 23:03:26 +08:00 |
|
|
Ke Bao
|
862dd76c76
|
Support NextN (MTP) speculative decoding for DeepSeek-V3/R1 (#3582)
|
2025-02-15 05:28:34 +08:00 |
|
|
Ke Bao
|
7e6d5fc694
|
Support Eagle cuda graph for Triton backend (#3500)
|
2025-02-12 02:27:45 +08:00 |
|
|
Ke Bao
|
2d61132374
|
Support Eagle2 for Triton backend (#3466)
|
2025-02-10 20:00:42 +08:00 |
|
|
Ke Bao
|
d8ad597048
|
Add deepseek-v3 a100 serving example (#3404)
|
2025-02-08 22:13:52 +08:00 |
|
|
Ke Bao
|
6792411e7f
|
[Doc] Add optimization option guide for deepseek v3 (#3349)
|
2025-02-06 23:28:09 +08:00 |
|
|
Ke Bao
|
a322051e31
|
Support custom mask for Triton attention (#3317)
|
2025-02-06 01:16:02 +08:00 |
|
|
Ke Bao
|
de5533341e
|
Update Triton extend backend interface (#3309)
|
2025-02-05 18:12:22 +08:00 |
|
|
Ke Bao
|
a07364ccc5
|
Update Triton decode backend interface (#3292)
|
2025-02-04 23:26:04 +08:00 |
|
|
Ke Bao
|
5317902670
|
Add test for fp8 torch compile (#3246)
|
2025-02-01 16:07:54 +08:00 |
|
|
Ke Bao
|
1ebe1d6de5
|
Optimize MoE topk with torch compile (#3236)
|
2025-02-01 01:36:50 +08:00 |
|
|
Ke Bao
|
c02e313914
|
Fix block wise fp8 torch compile (#3232)
|
2025-01-31 19:56:02 +08:00 |
|
|
Ke Bao
|
c23d5706f4
|
Update whl index path (#3128)
|
2025-01-25 23:57:09 +08:00 |
|
|
Ke Bao
|
67ad4338e1
|
Update tag name for whl release (#3127)
|
2025-01-25 23:14:35 +08:00 |
|
|
Ke Bao
|
665e5e85f6
|
Add step to update sgl-kernel whl index (#3110)
|
2025-01-25 02:03:01 +08:00 |
|
|
Ke Bao
|
a22f60a313
|
Add workflow for sgl-kernel cu118 release (#3109)
|
2025-01-24 22:30:30 +08:00 |
|
|
Ke Bao
|
6619f48e18
|
Fix cu118 group gemm compile issue (#3097)
|
2025-01-24 15:19:09 +08:00 |
|
|
Ke Bao
|
7bad7e75bf
|
Add shapes for int8 gemm benchmark (#3093)
|
2025-01-24 12:27:30 +08:00 |
|
|
Ke Bao
|
6fc37bd8ee
|
Fix sgl-kernel compile for sm80 (#3046)
|
2025-01-22 16:49:08 +08:00 |
|
|
Ke Bao
|
0ac019f171
|
Support sm90 Int8 gemm (#3035)
|
2025-01-21 22:21:54 +08:00 |
|
|
Ke BaoandHandH1998
|
5dfcacfcb1
|
Add compile flags for cutlass 3.x (#3013)
Co-authored-by: HandH1998 <1335248067@qq.com>
|
2025-01-21 00:04:12 +08:00 |
|
|
Ke Bao
|
41a0ccd4f1
|
Add clang-format check to sgl-kernel ci (#3012)
|
2025-01-20 23:22:19 +08:00 |
|
|
Ke Bao
|
656dcc1a99
|
Remove fp8 monkey patch (#2960)
|
2025-01-18 15:00:29 +08:00 |
|
|
Ke Bao
|
dc2ac0cbdb
|
Update pr template (#2951)
|
2025-01-18 00:44:16 +08:00 |
|
|
Ke Bao
|
d47c5101f1
|
Add ut for qwen model (#2947)
|
2025-01-18 00:03:54 +08:00 |
|
|
Ke Bao
|
53e6552fed
|
Fix qwen accuracy issue (#2945)
|
2025-01-17 22:35:26 +08:00 |
|
|
Ke Bao
|
f3e9b4894b
|
Fix sgl-kernel ci (#2938)
|
2025-01-17 17:26:21 +08:00 |
|
|
Ke Bao
|
58f3f2b840
|
Add CI for sgl-kernel (#2924)
|
2025-01-17 01:26:51 +08:00 |
|
|
Ke Bao
|
bfbda62c8b
|
Add ut for w8a8 int8 quantization (#2897)
|
2025-01-15 18:29:14 +08:00 |
|
|
Ke Bao
|
cc0485bef2
|
Support w8a8 int8 quantization config (#2881)
|
2025-01-14 17:07:49 +08:00 |
|
|
Ke Bao
|
c19d84829c
|
Adjust flashinfer workspace size for Qwen2 models (#2879)
|
2025-01-14 13:34:22 +08:00 |
|
|
Ke Bao
|
f3516c2894
|
Fix quant kernel accuracy issue (#2865)
|
2025-01-13 20:32:17 +08:00 |
|
|
Ke Bao
|
85b2e05770
|
Add int8 quant kernel (#2848)
|
2025-01-13 13:16:58 +08:00 |
|
|
Ke Bao
|
b5fb4ef58a
|
Update modelopt config and fix running issue (#2792)
|
2025-01-08 18:04:30 +08:00 |
|
|
Ke Bao
|
58f9060efe
|
Update int8 gemm config (#2774)
|
2025-01-07 19:47:37 +08:00 |
|
|
Ke Bao
|
0f3eb1d294
|
Support cutlass Int8 gemm (#2752)
|
2025-01-06 22:51:22 +08:00 |
|
|
Ke Bao
|
06dd2eab84
|
Remove unused var in moe_align_kernel (#2751)
|
2025-01-06 22:13:28 +08:00 |
|
|
Ke Bao
|
439f65809f
|
Fix sgl-kernel cu118 compile issue (#2750)
|
2025-01-06 21:59:31 +08:00 |
|
|
Ke Bao
|
b4403985d0
|
Add cutlass submodule for sgl-kernel (#2676)
|
2024-12-31 14:28:29 +08:00 |
|
|
Ke Bao
|
b02da24a5b
|
Refactor sgl-kernel build (#2642)
|
2024-12-30 18:07:01 +08:00 |
|
|
Ke Bao
|
8a2681e26a
|
Update readme (#2625)
|
2024-12-28 13:39:56 +08:00 |
|
|
Ke Bao
|
e835a50021
|
Reorg moe code (#2563)
|
2024-12-24 01:10:22 +08:00 |
|
|
Ke Bao
|
0ba2c58947
|
Remove cuda graph batch size adjustment for dp attention (#2484)
|
2024-12-14 23:53:54 +08:00 |
|
|
Ke Bao
|
2f9bd0fafd
|
Fix correctness issue for triton decoding kernel (#2479)
|
2024-12-14 16:50:54 +08:00 |
|
|
Ke Bao
|
61dec545b0
|
Remove unused vars in the triton backend (#2401)
|
2024-12-08 03:37:03 -08:00 |
|
|
Ke Bao
|
7dc66fcb40
|
Optimize Triton decoding kernel for long context (#2394)
|
2024-12-08 01:17:37 -08:00 |
|
|
Ke Bao
|
4a63c181f1
|
Fix AWQ with enable MLA (#2364)
|
2024-12-06 00:46:48 +08:00 |
|
|
Ke Bao
|
ec52464dde
|
MLA prefill w/o weight absorption (#2349)
|
2024-12-05 01:50:28 +08:00 |
|
|
Ke Bao
|
c5f865013e
|
Fix grid size in Triton decoding kernel (#2134)
|
2024-11-23 16:51:46 +08:00 |
|
|
Ke Bao
|
699384cb01
|
Set schedule policy more conservative for DP attention (#2096)
|
2024-11-19 20:57:18 -08:00 |
|
|
Ke Bao
|
62832bb272
|
Support cuda graph for DP attention (#2061)
|
2024-11-17 16:29:20 -08:00 |
|
|
Ke Bao
|
976bc302e5
|
Support DP MLA (#1970)
|
2024-11-16 09:01:43 +00:00 |
|
|
Ke Bao
|
b808a38365
|
Filter empty prompt in random bench serving (#2011)
|
2024-11-12 14:53:41 +08:00 |
|
|
Ke Bao
|
16eb33ffe2
|
Update vocab embedding deps and add TP switch (#1856)
|
2024-10-31 20:13:07 -07:00 |
|
|
Ke Bao
|
c77762d57f
|
Fix Triton decode kernel & ut (#1819)
|
2024-10-27 10:54:38 -07:00 |
|
|
Ke Bao
|
d10b933a36
|
Fix srt dependency (#1685)
|
2024-10-16 08:21:20 -07:00 |
|
|
Ke Bao
|
68f8b60d22
|
Fix chunked prefill condition (#1594)
|
2024-10-07 06:34:14 +00:00 |
|
|
Ke Bao
|
8d4ed42ad5
|
MoE torch compile (#1497)
|
2024-09-24 01:46:59 -07:00 |
|
|
Ke Bao
|
b8ccaf4d73
|
Add MLA gsm8k eval (#1484)
|
2024-09-21 11:16:13 +08:00 |
|