Commit Graph

11116 Commits

Author SHA1 Message Date
Yuan Luo
828dec1c7c [VLM] Tiny: Unify VLM environment variables (#15572)
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
2025-12-22 17:32:37 +08:00
ryang
575a49dc0e [diffusion] chore: remove default post-denoising dit offload in local mode (#15573) 2025-12-22 17:01:35 +08:00
fzyzcjy
e62e17442e Tiny enable soft watchdog in CI for stuck without logs (#15616) 2025-12-22 17:01:04 +08:00
fzyzcjy
d5431ff894 Tiny add stuck simulation (#15613) 2025-12-22 17:00:18 +08:00
fzyzcjy
454a2544f2 Support soft watchdog for tokenizer/detokenizer/dp-controller processes (#15607) 2025-12-22 16:59:16 +08:00
fzyzcjy
89619a9904 Tiny avoid EnvField misuse (#15612) 2025-12-22 16:20:47 +08:00
Hexq0210
cb30d056e3 add decode round robin policy (#15164) 2025-12-22 14:48:52 +08:00
Qiaolin Yu
677930c276 Add glm-4.6-fp8 with/without mtp in nightly ci (#15566) 2025-12-21 22:27:02 -08:00
Liangsheng Yin
beae3f961c Adapt fixture-kit to gsm8k mixin (#15599) 2025-12-22 14:19:35 +08:00
Simo Lin
1167867e8d [model-gateway] add retry support to OpenAI router chat endpoint (#15589) 2025-12-21 20:28:51 -08:00
fzyzcjy
ad7f35fb9d Support gsp send routing id in bench serving (#15588) 2025-12-22 11:32:24 +08:00
fzyzcjy
f4100732b8 Tiny fix bench serving GSP mode cache file strategy (#15587) 2025-12-22 11:27:55 +08:00
Baizhou Zhang
468931b572 [Tiny]Move deepseek fp4 cutlass moe test to per-commit test (#15565) 2025-12-21 18:08:07 -08:00
Simo Lin
796969caf0 Optimize Rust CI builds with proper sccache configuration (#15581) 2025-12-21 17:32:13 -08:00
Simo Lin
122c250336 [model-gateway] add retry and circuit breaker support to gRPC routers (#15585) 2025-12-21 17:12:36 -08:00
FlyPanda
a3a552232d [feature] support hicache-3fs usrbio lib build for ubuntu24.04 (#15230) 2025-12-21 17:00:38 -08:00
Chenxi Li
0bf95e6d69 Fix type mismatch in LoRA batch validation causing assertion failures (#15427) 2025-12-21 15:54:41 -08:00
Qiaolin Yu
a92de891b8 Split dpsk fp4 4 gpu tests and move the mtp part to real stage b (#15553) 2025-12-21 15:51:43 -08:00
Simo Lin
b9d786059f [model-gateway] refactor WorkerManager with fan_out helper and thin handlers (#15583) 2025-12-21 15:29:37 -08:00
Simo Lin
1354063a48 [model-gateway] add WorkerService abstraction for worker business logic (#15580) 2025-12-21 14:35:35 -08:00
Qiaolin Yu
254de6d2fd Add triton_fused_moe config for GLM-4.6-FP8 tp8 blackwell (#15569) 2025-12-21 13:41:22 -08:00
Jincong Chen
350fbbf4dc fix ds3.2 nsa backend prefill TBO (#14901) 2025-12-21 13:16:46 -08:00
sglang-bot
a39126672a chore: bump sgl-kernel version to 0.3.20 (#15564) 2025-12-21 13:15:23 -08:00
Simo Lin
e1dcd0df3e [model-gateway] minor code clean up (#15578) 2025-12-21 11:00:32 -10:00
Liangsheng Yin
393e2f9b62 Revert "[FusedMoE] Fix fused w13 tp sharded weight loading" (#15579) 2025-12-22 04:15:24 +08:00
Liangsheng Yin
8766a1dd24 [1 / N] Clean up logprob utils (#15509) 2025-12-22 03:12:25 +08:00
shuwenn
1d9ba2ce4d [model-gateway] Use UUIDs for router-managed worker resources (#15540) 2025-12-21 07:40:03 -10:00
Haoran Wang
ef001fb811 [model-gateway] /parse/easoning and parse/function_call for sgl-model-gateway (#15568) 2025-12-21 07:39:24 -10:00
sunxxuns
c69c1c4f07 [CI] Fix AMD CI to exclude multimodal_gen from main_package filter (#15558) 2025-12-21 16:58:17 +08:00
Junrong Lin
bed301a5ac [Feature] Enable return routed experts (#12162)
Co-authored-by: yizhang2077 <1109276519@qq.com>
Co-authored-by: Liangsheng Yin <lsyincs@gmail.com>
2025-12-21 15:16:43 +08:00
Ke Bao
8fe3e37468 Support piecewise cuda graph for dsv3 fp4 (#15531) 2025-12-21 14:50:32 +08:00
YAMY
6014365564 [EAGLE] Fix slow Triton compilation in EAGLE KV cache copy by chunking large num_locs_upper (#15111) 2025-12-21 14:14:14 +08:00
Yinghai Lu
fc05acc2c7 [FusedMoE] Fix fused w13 tp sharded weight loading (#15432) 2025-12-21 13:59:36 +08:00
Mick
1ed946680a [diffusion] bench: improve bench_serving by adding more controlling args (#15554) 2025-12-21 13:37:45 +08:00
Mick
d7fbe73bf2 [diffusion] chore: minor improvements and typo-fixing (#15556) 2025-12-21 13:37:10 +08:00
Xiaoyu Zhang
42bff706df [diffusion] profiling: simplify --perf-dump-path JSON output (remove duplicate denoise steps) (#15537)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-12-21 12:56:46 +08:00
Haoran Wang
26704c23c0 [model-gateway]: Tool parser for glm47 (#15520) 2025-12-20 18:07:51 -10:00
Alison Shao
43b7c17474 [CI] Fix /rerun-stage command by using requests for workflow dispatch (#15447) 2025-12-20 19:50:56 -08:00
Douglas Yang
96740d6983 feature: revamp nightly tests with combined runner (#15324) 2025-12-20 19:25:22 -08:00
Alison Shao
9a3bdf2c95 [CI] Migrate CUDA Graph tests to test/registered/cuda_graph/ (#15436) 2025-12-20 18:55:39 -08:00
Xiaoyu Zhang
4b351f6b95 Apply new moe align block size kernel (#14134) 2025-12-21 10:13:32 +08:00
Xiaoyu Zhang
7fa4906f4f [sgl-kernel] Streamline kernel size report (Top 20 only) and clean up (#15552) 2025-12-21 10:00:47 +08:00
Yuan Luo
050f108c29 Optimize Bailing-MoE with FlashInfer Fused All-Reduce (#15526)
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
2025-12-20 17:34:04 -08:00
Xinyuan Tong
47cdb65a45 fix: update argument extraction in R1 chat template (#15547)
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
2025-12-21 09:18:49 +08:00
shuwenn
1d90b194b2 [model-gateway] bugfix: backward compatibility for GET endpoints (#15413) 2025-12-20 10:37:53 -10:00
Praneth Paruchuri
537ef18d17 [model-gateway] Optimize WASM Runtime with Instance Pooling and Component Caching (#15515) 2025-12-20 10:27:02 -10:00
Simo Lin
69412ccb1f [model-gateway] add model gateway multi-arch docker build, test and document docker image (#15544) 2025-12-20 11:56:59 -08:00
Simo Lin
d3885d4ba6 Fix docker gateway image name and add latest tag (#15542) 2025-12-20 11:05:03 -08:00
Xinyuan Tong
0a346d3bd9 feat: Add limit-mm-data-per-request argument to server arguments (#15418)
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
2025-12-20 10:44:47 -08:00
Mick
bc18cb8631 [diffusion] refactor: change zmq socket type to router for scheduler (#15479) 2025-12-21 00:39:54 +08:00