Commit Graph

5345 Commits

Author SHA1 Message Date
ykwd
4bb08f6e07 [Hicache] Evaluate Per-Round Metrics in Multiturn Bench (#10203)
Co-authored-by: Teng Ma <sima.mt@alibaba-inc.com>
2025-09-15 19:34:40 -07:00
kk
ec272dda9c Temporay work-around for rocm 7.0.0 alpha with enabling data-parallel issue (#10434)
Co-authored-by: wunhuang <wunhuang@amd.com>
Co-authored-by: Sai Enduri <saimanas.enduri@amd.com>
2025-09-15 19:08:04 -07:00
scut-cbq
a220c14f81 fix crash of DeepSeek-V3 update_weights_from_disk (#8863)
Co-authored-by: parkeychen <parkeychen@tencent.com>
2025-09-16 09:45:15 +08:00
Chang Su
35ef3f2902 [router] fix worker registration in multi model mode (#10486) 2025-09-15 21:05:00 -04:00
Lianmin Zheng
31fb19a0a2 [Auto Sync] Update registry.py (20250915) (#10484)
Co-authored-by: cctry <shiyang@x.ai>
2025-09-15 17:34:28 -07:00
Lifu Huang
3f41b48c40 [2/2] Introduce Chunked-SGMV kernels and corresponding LoRA backend for improved performance (#10286) 2025-09-15 16:04:03 -07:00
Chang Su
2689f0bf02 [router] multi model registration fix (#10481) 2025-09-15 15:22:21 -07:00
Yineng Zhang
5207424014 chore: bump v0.3.10 sgl-kernel (#10478) 2025-09-15 15:20:09 -07:00
Liangsheng Yin
c3c26f76b3 [Env] minimal version for organizing envs (#10479) 2025-09-16 03:51:25 +08:00
Liangsheng Yin
2cf811a9da Fix --dataset-path in bench_one_batch_server (#10475) 2025-09-16 02:55:02 +08:00
fzyzcjy
3b25dc127a [1/2] Speed up trtllm_mla attention backend (>10% e2e) (#10473) 2025-09-15 11:53:21 -07:00
Yineng Zhang
5c08d7d21d fix: resolve sgl-kernel ut (#10476) 2025-09-15 11:42:48 -07:00
Praneth Paruchuri
a45d9a4ee8 model: support solar (#8189) 2025-09-16 02:21:13 +08:00
Jonas
28c79dc84a fix: gpt-oss streaming dropping normal content when tools are provided but not used (#9657) 2025-09-15 11:02:32 -07:00
Kevin Tuan
1fcccda4b2 fix(internvl): fix accuracy issue of normalization (#10375) 2025-09-16 01:56:01 +08:00
Sahithi Chigurupati
79acec4fe7 [CI] Fix runner for sgl-kernel (#9887)
Signed-off-by: Sahithi Chigurupati <chigurupati.sahithi@gmail.com>
2025-09-15 10:55:48 -07:00
Yingchun Lai
b1721edbac [PD metrics] Add latency Histogram metrics of each stage for generate requests (#8710) 2025-09-16 01:52:49 +08:00
Jiayi Yan
57234d0c9c [bugfix] fix typo (#10471) 2025-09-15 07:29:20 -07:00
Chang Su
b93acd7020 [router] minor code clean up in server startup (#10470) 2025-09-15 07:28:25 -07:00
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