Commit Graph

2018 Commits

Author SHA1 Message Date
Yineng Zhang
4fe92bfca5 fix mla test (#3469) 2025-02-10 21:12:00 +08:00
Ying Sheng
d23cb9a01e [Eagle] reduce one draft forward (#3468) 2025-02-10 20:21:49 +08:00
Ke Bao
2d61132374 Support Eagle2 for Triton backend (#3466) 2025-02-10 20:00:42 +08:00
Yineng Zhang
cddb1cdf8f chore: bump v0.4.2.post4 (#3459) 2025-02-10 14:12:16 +08:00
Yineng Zhang
fa1b40e00d use nvcr.io/nvidia/tritonserver:24.04-py3-min as base image (#3457) 2025-02-10 13:52:33 +08:00
Baizhou Zhang
c45cab1c00 [Fix] Fix accuracy bug and refactor codes for lora (#3413) 2025-02-10 13:29:00 +08:00
Yineng Zhang
27c4c9cf52 remove _grouped_size_compiled_for_decode_kernels (#3453) 2025-02-10 13:01:21 +08:00
Ying Sheng
52a492a16e Update contribution_guide.md (#3452) 2025-02-10 12:53:47 +08:00
Yineng Zhang
36f6fc5093 feat: enable ragged fa3 by default on hopper 12.4+ (#3442) 2025-02-10 07:43:01 +08:00
Yineng Zhang
d87272750b fix ci (#3441) 2025-02-10 04:22:28 +08:00
Yineng Zhang
6239d0b2e7 chore: bump sgl-kernel v0.0.3.post3 (#3440) 2025-02-10 04:00:52 +08:00
Yineng Zhang
4cfd3add6d support version in sgl-kernel (#3439) 2025-02-10 03:49:52 +08:00
Shi Shuai
20cf910d8f [docs] Update quantization documentation (#3437)
Co-authored-by: zhaochenyang20 <zhaochenyang20@gmail.com>
Co-authored-by: jamessand <shazhizhou0@gmail.com>
2025-02-09 10:39:49 -08:00
Wenxuan Tan
0af1d239cb [Docs] Add quantization docs (#3410)
Co-authored-by: yinfan98 <1106310035@qq.com>
2025-02-10 02:16:21 +08:00
Yineng Zhang
85986bb978 compatible with new outlines (#3435) 2025-02-10 01:51:30 +08:00
Yineng Zhang
64c8713573 remove activation dependency in fused_moe (#3433) 2025-02-10 01:18:57 +08:00
Yineng Zhang
1646149a83 fix draft cuda graph capture failure (#3431) 2025-02-09 23:16:20 +08:00
Yineng Zhang
bc72e5bd32 add cuda graph capture failure possible solution (#3430) 2025-02-09 22:57:11 +08:00
Yineng Zhang
014cab4dd2 update forward_return_lse (#3425) 2025-02-09 20:18:44 +08:00
Yineng Zhang
4d2dbeaca7 remove cutex dependency (#3422) 2025-02-09 18:33:20 +08:00
Yineng Zhang
29daf498cd fix cu118 link issue (#3421) 2025-02-09 18:16:44 +08:00
Shi Shuai
6702592d0e [docs] Add multi-node inference example for SLURM in documentation (#3408)
Co-authored-by: zhaochenyang20 <zhaochen20@outlook.com>
Co-authored-by: aflah02 <aflah20082@iiitd.ac.in>
2025-02-08 21:45:14 -08:00
Yineng Zhang
60abdb3e7c minor: cleanup test_eagle_infer (#3415) 2025-02-09 09:34:30 +08:00
Ying Sheng
7b4e61fff3 [Fix] Fix eagle with disable cuda graph (#3411) 2025-02-09 08:40:00 +08:00
Yineng Zhang
6222e1c228 add disable cuda graph unit test for eagle 2 (#3412) 2025-02-09 08:02:56 +08:00
Yineng Zhang
fad315cb8e fix EAGLE 2 non greedy case (#3407)
Co-authored-by: Ying Sheng <sqy1415@gmail.com>
2025-02-09 07:28:34 +08:00
Yineng Zhang
f90db8bc07 fix typo 2025-02-08 22:16:42 +08:00
Ke Bao
d8ad597048 Add deepseek-v3 a100 serving example (#3404) 2025-02-08 22:13:52 +08:00
GaoYuYang
849f58d617 Update fused_moe's benchmark (#3346) 2025-02-08 21:58:21 +08:00
yiakwy-xpu-ml-framework-team
64480df495 [BUG] fix moe benchmark when bs*seq is small (#3382) 2025-02-08 15:39:44 +08:00
lukec
4530136e61 Add H20 fp8 w8a8 gemm config (#3386) 2025-02-08 15:36:31 +08:00
Zachary Streeter
0a6f18f068 added amd_configure.md to references (#3275)
Co-authored-by: HAI <hixiao@gmail.com>
Co-authored-by: Yineng Zhang <me@zhyncs.com>
Co-authored-by: zhaochenyang20 <zhaochen20@outlook.com>
2025-02-07 08:50:49 -08:00
Yineng Zhang
c1f5f99f60 chore: bump v0.4.2.post3 (#3369) 2025-02-07 08:20:03 -08:00
Yineng Zhang
fa82dfccdd fix EagleVerifyInput (#3378) 2025-02-07 22:30:43 +08:00
Yineng Zhang
5da3d21c8b update pr-test ci (#3376) 2025-02-07 21:08:35 +08:00
Yineng Zhang
f287037673 update sgl-kernel version (#3374) 2025-02-07 20:51:06 +08:00
Yineng Zhang
f9905d59a8 support speculative decoding kernel in sgl-kernel (#3373)
Co-authored-by: Ying Sheng <sqy1415@gmail.com>
2025-02-07 20:29:51 +08:00
Yineng Zhang
45c87e083f fix undefined symbol cudaGetDriverEntryPointByVersion (#3372) 2025-02-07 19:32:45 +08:00
Yineng Zhang
2b1808cec4 update unit test in AMD CI (#3366) 2025-02-07 17:25:16 +08:00
lizamd
e868d0b60e update waves_per_eu to 1 (#3356) 2025-02-07 13:08:06 +08:00
Shi Shuai
591e751e07 Fix: Runtime error for function calling (#3300) 2025-02-06 20:52:01 -08:00
Chayenne
40022d075a Feature: Fix the binding error in Llama (#3355) 2025-02-06 20:19:24 -08:00
Liangjun Song
823148e7f0 Docs: Add deepseek usage and add multi-node, credit to lycanlancelot (#3314)
Co-authored-by: Shi Shuai <126407087+shuaills@users.noreply.github.com>
Co-authored-by: Chayenne <zhaochen20@outlook.com>
Co-authored-by: Yineng Zhang <me@zhyncs.com>
2025-02-06 19:45:00 -08:00
Chayenne
76ca91dff2 Docs/CI: Enable Fake Finish for Docs Only PR (#3350) 2025-02-06 19:33:31 -08:00
Xiaoyu Zhang
cdae77b03d optimize moe_align_kernel cuda (#3347) 2025-02-07 00:53:46 +08:00
Yineng Zhang
adeee15204 fix sgl-kernel build failure on AMD (#3352) 2025-02-07 00:35:59 +08:00
Ke Bao
6792411e7f [Doc] Add optimization option guide for deepseek v3 (#3349) 2025-02-06 23:28:09 +08:00
Yineng Zhang
7348d9627e add AMD guide for DeepSeek-R1 (#3338) 2025-02-06 16:54:40 +08:00
Yineng Zhang
25ed22b685 update pull request template (#3337) 2025-02-06 16:48:02 +08:00
saienduri
200d3b1608 Add sgl-kernel to MI300 CI paths tested. (#3335)
Co-authored-by: HAI <hixiao@gmail.com>
2025-02-06 00:45:38 -08:00