Commit Graph

5326 Commits

Author SHA1 Message Date
Yineng Zhang
86a32bb5cd chore: bump v0.5.3rc0 (#10468) 2025-09-15 03:55:18 -07:00
Yineng Zhang
5afd036533 feat: support pip install sglang (#10465) 2025-09-15 03:09:17 -07:00
fzyzcjy
059c13de5c Fix trtllm_moe wrong correction bias (#10440) 2025-09-15 01:02:05 -07:00
Lianmin Zheng
50dc0c1e9c Run tests based on labels (#10456) 2025-09-15 00:29:20 -07:00
Jimmy_L
76becc1dbc Add rtx5880 moe triton (#10439) 2025-09-15 00:12:10 -07:00
hzh0425
2a37b24d23 [HotFix]: Hot fix import path in 3fs_bench_client.py (#10463) 2025-09-14 23:45:46 -07:00
Lianmin Zheng
f73aae0bfc Update GITHUB_TOKEN secret for documentation push (#10458) 2025-09-14 21:59:13 -07:00
Chang Su
69b35793a0 [router] fix logger ordering git ctx (#10457) 2025-09-14 21:37:21 -07:00
ooapex
957482c8f2 [router] add dependency for router (#10401) 2025-09-14 21:14:14 -07:00
Jimmy
3795b6a43f fix(server_args): Skip chunked_prefill_size validation when disaggregation mode is decode (#10358) 2025-09-15 12:13:35 +08:00
Simo Lin
7eccbe992d [router] fix service discovery and mcp ut (#10449) 2025-09-14 21:07:23 -07:00
Mick
0549f21c60 fix: fix max_new_tokens uninitialized error (#9343) 2025-09-15 12:06:55 +08:00
Lianmin Zheng
b354e3c90d [CI] Fix token key in label-pr.yml workflow (#10452) 2025-09-14 20:45:53 -07:00
Lianmin Zheng
65e6f48ce4 Update permissions in label-pr.yml (#10450) 2025-09-14 20:41:43 -07:00
Lianmin Zheng
0ec580a86c Fix label PR (#10445) 2025-09-14 20:33:09 -07:00
Vincent Zhong
0b14159fc4 Add reasoning examples for GPT-OSS in Markdown examples (#9626) 2025-09-15 11:27:40 +08:00
Vincent Zhong
1489cd6c02 [docs / oneliner] update mmmu docs instruction (#9768)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-09-15 11:26:39 +08:00
Yingchun Lai
fc2c3a3d8e metrics: support customer labels specified in request header (#10143) 2025-09-14 20:00:08 -07:00
Lianmin Zheng
8f6a175803 Fix label pr for ci (#10441) 2025-09-14 19:48:06 -07:00
fzyzcjy
010181388c Tiny fix wrong naming (#10437) 2025-09-14 19:24:41 -07:00
Cheng Wan
4844fac91d Refactor TopK to ensure readability and extensibility (#9338) 2025-09-14 19:16:25 -07:00
Lianmin Zheng
b7d385e812 automatically label pr for ci (#10435) 2025-09-14 19:13:11 -07:00
Liangsheng Yin
305c9e8c2d [4/N]DP refactor: support watching mode get_load and shortest queue strategy (#10201) 2025-09-15 10:06:08 +08:00
fzyzcjy
ca63f075b7 Revert "Fix FA4 import cause moe_fused_gate output be illegal memory" (#10432) 2025-09-14 19:03:27 -07:00
Jintao Zhang
f9ee6ae17a [router]: Add Embedding routing logic (#10129)
Signed-off-by: Jintao Zhang <zhangjintao9020@gmail.com>
Co-authored-by: Waël Boukhobza <wawa_wael@live.fr>
2025-09-14 18:44:35 -07:00
Yineng Zhang
dcee42c200 feat: add dsv3 fp4 cutlass moe etp ut (#10433) 2025-09-14 18:44:09 -07:00
fzyzcjy
258d02c86d Fix correction bias undefined behavior for nvfp4 models (#10426) 2025-09-14 18:41:09 -07:00
Ke Bao
60d7beda6b Add split tile size for Triton attention (#10425) 2025-09-14 17:35:49 -07:00
Cheng Wan
2f8ba6fe82 [Fix] MoE: fix w8a8_fp8 MoE and add tests to cover this code path (#10429) 2025-09-14 17:34:28 -07:00
Yineng Zhang
7ce6c10eb6 fix: enable cu124 and cu128 build on main push (#10431) 2025-09-14 16:19:35 -07:00
Yineng Zhang
55025b9282 fix: use latest flashinfer (#10428) 2025-09-14 15:07:14 -07:00
Feng Su
4c21b09074 [Feature] Sglang Tracing: Fine-Grained Tracking for Request Latency - Part 1 (#9962)
Signed-off-by: Feng Su <sufeng@linux.alibaba.com>
Signed-off-by: Huaixin Chang <changhuaixin@linux.alibaba.com>
Signed-off-by: Peng Wang <rocking@linux.alibaba.com>
2025-09-15 02:08:02 +08:00
艾力可
165abeebca Typo: in --enable-custom-logit-processor: agree with cli arg (#10076) 2025-09-14 02:27:09 -07:00
Yingchun Lai
21ca4c3afa [PD metrics] Fix some uncompleted PD related metrics (#8627) 2025-09-14 02:26:58 -07:00
fzyzcjy
e3cf812f7d Fix sgl-kernel + srt CI (#10419) 2025-09-14 01:44:47 -07:00
fzyzcjy
4da5533682 Support profile args in Engine API (#6539) 2025-09-14 01:21:10 -07:00
fzyzcjy
ac964d2e58 Support global scale in addition to per expert scale for cutedsl moe (#10270) 2025-09-14 01:17:00 -07:00
fzyzcjy
fa46e2bd40 Support offloading in fp8 (#9948) 2025-09-14 01:14:28 -07:00
fzyzcjy
b047b553c2 [2/2] Speed up prefill mla attention concat (#10157) 2025-09-14 01:12:04 -07:00
fzyzcjy
a0f844ed5a Let sgl-kernel changes be tested on srt (#10313) 2025-09-14 01:09:17 -07:00
fzyzcjy
2df532ef20 Fix the global scale fix does not support EPLB and improve enabling condition (#10369) 2025-09-14 01:07:47 -07:00
fzyzcjy
abea9250da Auto determine sgl kernel version in blackwell CI (#10318) 2025-09-14 01:06:30 -07:00
Ximingwang-09
b3c977622f Add h200 fused moe config for Qwen3-Next (#10404)
Co-authored-by: 纬杭 <ximing.wxm@antgroup.com>
2025-09-13 23:48:46 -07:00
Yuxuan Zhang
b8347b40b1 Add self.capture_aux_hidden_states For GLM-4.5V (#10228) 2025-09-13 23:31:55 -07:00
fzyzcjy
72dfa96aeb Fix cutlass moe accuracy drop caused by attention UB from DP padding mode (#10414) 2025-09-13 22:29:09 -07:00
lijin23
05b01ef4da fix duplicated logger in eager_utils (#10410) 2025-09-13 22:25:40 -07:00
Liangsheng Yin
55a6e644b0 [Hack] Add pd-disaggregation decode polling interval (#10411) 2025-09-14 10:18:23 +08:00
Liangsheng Yin
6897e06b69 Remove repeatedly lists adding in init_incremental_detokenization (#10412) 2025-09-14 10:05:52 +08:00
Sundara Raman Ramachandran
a360511d7b [Generative Score API] Scoring(Prefill-only) optimizations. (#9748) 2025-09-14 01:57:06 +08:00
Sundara Raman Ramachandran
94d0f656fb [Performance] Dynamic Batch Tokenizer (#9382) 2025-09-14 01:56:04 +08:00