Commit Graph

2789 Commits

Author SHA1 Message Date
Atream
4f838c09cd [PD] Transfer hidden states for mtp when disaggregation (#7242) 2025-06-19 11:22:47 -07:00
Chang Su
d20a073bc3 Put _normalize_rid before other normalization in io_struct (#7363) 2025-06-19 11:21:25 -07:00
DarkSharpness
47367b768d [Refactor] Clean up radix cache related API (#7303)
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
2025-06-20 00:58:48 +08:00
fzyzcjy
650127a173 Reintroduce tiny fix sampler error when prob is not contiguous (#7354) 2025-06-19 09:39:34 -07:00
Stefan He
3774f07825 Multi-Stage Awake: Support Resume and Pause KV Cache and Weights separately (#7099) 2025-06-19 00:56:37 -07:00
Jinn
ffd1a26e09 Add more refactored openai test & in CI (#7284) 2025-06-18 13:52:55 -07:00
Simo Lin
09ae5b20f3 Merge PDLB (Prefill-Decode Load Balancer) into SGLang Router (#7096) 2025-06-19 02:28:15 +08:00
fzyzcjy
9c6a0656a3 Fix profiler error when there are idle passes (#7003) 2025-06-18 10:55:01 -07:00
ch-tiger1
2ae809c5c1 Fix mini_lb for PD with long output: limit chunk size of decode response (#7301)
Signed-off-by: ch-tiger1 <xyz@ch-tech.ip-ddns.com>
Co-authored-by: ch-tiger1 <xyz@ch-tech.ip-ddns.com>
2025-06-18 10:46:46 -07:00
ishandhanani
31fccf5a4f chore: change logs fromINFO to DEBUG for dp and add force quit for tokenizer manager (#7251) 2025-06-18 01:36:43 -07:00
YanbingJiang
094c116f7d Update python API of activation, topk, norm and rope and remove vllm dependency (#6614)
Co-authored-by: Wu, Chunyuan <chunyuan.wu@intel.com>
Co-authored-by: jianan-gu <jianan.gu@intel.com>
Co-authored-by: sdp <sdp@gnr799219.jf.intel.com>
2025-06-17 22:11:50 -07:00
Zhiqiang Xie
e56685ac1b Upstreaming hicache bug fixes (#7267) 2025-06-17 17:44:57 -07:00
shangmingc
c26d7349d3 [PD] Add custom memory pool option to support Mooncake PD with NVLink (#7264)
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
2025-06-17 17:21:37 -07:00
shangmingc
ceaa85c9e6 [PD] Support get local ip from NIC for PD disaggregation (#7237)
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
2025-06-17 17:19:26 -07:00
Yineng Zhang
4f204db57c fix: resolve b200 dsv3 mtp issue (#7286) 2025-06-17 16:22:46 -07:00
AniZpZ
3eb4a800e8 Fix AWQ Dequant and Weight Loading of deepseek v2 (#6842) 2025-06-17 13:45:10 -07:00
Chang Su
e726131523 bugfix(tool call ebnf): Fix EBNF generation for optional function parameters (#7283) 2025-06-17 13:36:07 -07:00
Charles Chen
8c16da334e Fix Deepseek R1 0528 FP4 tensor name mismatch issue during weights loading. (#7164) 2025-06-17 11:26:23 -07:00
Yijie Zhu
a39d928782 support qwen2 running on ascend npu device (#7022)
Co-authored-by: 刁莹煜 <diaoyingyu1@hisilicon.com>
2025-06-17 11:24:10 -07:00
u4lr451
10d60cd41b feat: mtp support dp-attention (#6081)
Co-authored-by: austindeng <austindeng@tencent.com>
Co-authored-by: tianqilin.99 <tianqilin.99@bytedance.com>
Co-authored-by: Qiaolin Yu <liin1211@outlook.com>
Co-authored-by: ch-wan <cwan39@gatech.edu>
2025-06-17 00:33:28 -07:00
kk
405780bcf0 [amd] Opt dsv3 moe (#7160)
Co-authored-by: wunhuang <wunhuang@amd.com>
2025-06-16 22:26:51 -07:00
yhyang201
1dffee31ac OAI Server Skeleton & Core Utility Endpoints (#7179) 2025-06-16 20:45:55 -07:00
Xinyuan Tong
70c471a868 [Refactor] OAI Server components (#7167)
Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
2025-06-16 20:45:20 -07:00
Lianmin Zheng
1a9c2c9214 Fix AMD speculative decoding (#7252) 2025-06-16 17:01:33 -07:00
KavioYu
873ae12cee support custom weight loader for model runner (#7122)
Co-authored-by: kavioyu <kavioyu@tencent.com>
2025-06-16 16:28:15 -07:00
Lianmin Zheng
c64290dcb5 Use seq_len_fill_value in the cuda graph runners (#7233) 2025-06-16 15:57:07 -07:00
Alex Sun
8e2363dc15 fix amd EP MoE FP8 issue (#7125) 2025-06-16 15:29:45 -07:00
Yineng Zhang
f9dc9dd28b chore: bump v0.4.7.post1 (#7248) 2025-06-16 15:20:29 -07:00
JieXin Liang
5ca07eed90 [fix] fix DeepGEMM blackwell input quant & ut & fix style and log (#7247) 2025-06-16 11:45:54 -07:00
woodx
e30ef368ab Feat/support rerank (#6058) 2025-06-16 10:50:01 -07:00
fzyzcjy
91a066ec6a Tiny remove comments about DeepEP on H20 (#7234) 2025-06-16 09:13:57 -07:00
Liangsheng Yin
c494386728 minor fix (#7245) 2025-06-16 23:30:26 +08:00
Lianmin Zheng
53a525bf33 [Eagle] Fix kernel call after updating speculative sampling kernels (#7231) 2025-06-16 07:25:59 -07:00
Lianmin Zheng
7ddf8e83d2 [EAGLE] Fix draft kv cache layout for fa3 and topk > 1 (#7239) 2025-06-16 05:47:51 -07:00
Lianmin Zheng
b1286a116a [EAGLE] Refactor code for page size > 1 & more simplifications (#7213) 2025-06-16 03:04:29 -07:00
Lianmin Zheng
21615cc3fe Minor style and doc fix (#7228) 2025-06-16 01:03:13 -07:00
Cheng Wan
3c2274fbee Implement gather before attn (#6378) 2025-06-15 21:08:56 -07:00
Baizhou Zhang
d2679f5109 Fix ChunkCache object has no attribute 'disable' (#7217) 2025-06-15 20:55:15 -07:00
Byron Hsu
96be97bfff Minor PD style fix (#7215) 2025-06-15 16:12:12 -07:00
Byron Hsu
88f9c347b2 [PD] use int32 for kv indices & get num_reserved_decode_tokens from server_args (#7214) 2025-06-15 11:51:03 -07:00
Lianmin Zheng
fff10809bf Revert "[EAGLE] Refactor code for page size > 1 & more simplifications" (#7210) 2025-06-15 02:48:00 -07:00
Lianmin Zheng
5f1ab32717 [EAGLE] Refactor code for page size > 1 & more simplifications (#7163) 2025-06-14 23:16:23 -07:00
Lianmin Zheng
38af4f68a9 Fix grammar abort & Minor style fixes (#7204) 2025-06-14 22:49:41 -07:00
Lianmin Zheng
a6305c7d50 Lianmin/simplify memory pool (#7202) 2025-06-14 22:25:37 -07:00
Lianmin Zheng
a023856b12 Move host memory pools into a separate file (#7200) 2025-06-14 21:31:42 -07:00
Byron Hsu
db0cc57e75 [PD] Support decode retract and update decode.py (#7196) 2025-06-14 19:48:05 -07:00
fzyzcjy
349bb2c92a Fix error when disabling new DeepGEMM (#7198) 2025-06-14 19:24:54 -07:00
JieXin Liang
ed89837cf4 chore: upgrade sgl-kernel v0.1.8.post2 (#7186)
Co-authored-by: zhyncs <me@zhyncs.com>
2025-06-14 18:26:18 -07:00
JieXin Liang
55561e2553 [fix] fix determine_num_fused_shared_experts (#7180) 2025-06-14 17:41:22 -07:00
Zhijian Liu
0bd67ba2bd Fix a minor bug related to DeepGEMM upgrade (#7191) 2025-06-14 16:54:40 -07:00