Commit Graph

2041 Commits

Author SHA1 Message Date
yizhang2077
98eecbda54 integrate blockwise fp8 kernel (#3529) 2025-02-13 04:39:33 +08:00
Yineng Zhang
4430c0a513 chore: bump 0.0.3.post5 sgl-kernel (#3530) 2025-02-13 01:51:46 +08:00
yizhang2077
640363ad20 support blockwise fp8 matmul kernel (#3267) 2025-02-13 01:49:33 +08:00
Liangsheng Yin
8616357a97 Fix deepseek awq v3 (#3450) 2025-02-12 22:09:52 +08:00
Zachary Streeter
8adbc78b30 added llama and cleaned up (#3503) 2025-02-12 18:48:30 +08:00
Xiaoyu Zhang
45e3a7bc41 use sgl_per_token_group_quant_fp8 kernel (#3493) 2025-02-12 18:40:42 +08:00
Yineng Zhang
b96e92e6e6 chore: bump 0.0.3.post4 sgl-kernel (#3523) 2025-02-12 17:28:36 +08:00
Xiaoyu Zhang
693c2600e0 refine deepseek_v3 launch server doc (#3522) 2025-02-12 17:27:07 +08:00
Mick
ced680663c doc: Support a new vLM (#3405)
Co-authored-by: zhaochenyang20 <zhaochen20@outlook.com>
2025-02-12 00:43:14 -08:00
Ata Fatahi
b8318aec48 Make NCCL NVLS configurable (#3502) 2025-02-12 03:25:06 +08:00
Yineng Zhang
2f48221033 docs: update install 2025-02-12 03:13:31 +08:00
HAI
d81ac4434e MI30x: More graph captures for larger batch sizes and concurrencies (#3420) 2025-02-12 03:04:38 +08:00
Zachary Streeter
2491cc928d add deepseek-v3 amd docker command (#3495) 2025-02-12 03:03:08 +08:00
Didier Durand
67c5de9286 fix router typo (#3496) 2025-02-12 03:00:57 +08:00
Didier Durand
1e2cf2b541 fix server_arguments typo (#3499) 2025-02-12 02:59:53 +08:00
Didier Durand
9490d15772 fix supported_models Qwen typo (#3498) 2025-02-12 02:59:18 +08:00
Didier Durand
eefcbdd353 fix deepseek_v3 typo (#3497) 2025-02-12 02:58:36 +08:00
Ke Bao
7e6d5fc694 Support Eagle cuda graph for Triton backend (#3500) 2025-02-12 02:27:45 +08:00
Wen-Heng (Jack) Chung
cadd5dbe6a Tune MI300X fused MoE Triton kernel JSON config. (#3492) 2025-02-11 10:27:25 -08:00
Xiaoyu Zhang
bb418ced80 optimize per token group quant fp8 (#3490) 2025-02-11 22:19:05 +08:00
yigex
fdf04a1426 [ROCm] Add ROCm tuning config to block gemm and Re-tune for AMD Radeon Graphics (#3418)
Co-authored-by: Bruce Xue <yigex@xilinx.com>
Co-authored-by: HAI <hixiao@gmail.com>
2025-02-10 23:55:04 -08:00
Jackmin801
5f0e7de339 [Feat] Return hidden states (experimental) (#3364)
Co-authored-by: Chayenne <zhaochen20@outlook.com>
2025-02-10 15:54:37 -08:00
Xiaoyu Zhang
2f47d710ae refine some typo (#3473) 2025-02-10 23:35:44 +08:00
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