Commit Graph

9885 Commits

Author SHA1 Message Date
Shangming Cai
c15fa1c577 [2/N] Update doc of Pipeline Parallelism with case study (#15684)
Signed-off-by: Shangming Cai <csmthu@gmail.com>
2025-12-23 20:56:15 +08:00
Tianyu Guo
fa2966983a Support PP for zmq_to_scheduler (#15312) 2025-12-23 17:07:55 +08:00
Douglas Yang
f9dd90ac35 fix: increasing H200 test timeout (#15600) 2025-12-23 01:00:37 -08:00
Bingxu Chen
66902e0f1b [AMD] CI - Improve image discovery with remote registry fallback (#15463) 2025-12-22 23:04:58 -08:00
yctseng0211
e50f356f6f [AMD] CI - Detect the aiter version and rebuild if needed (#15460) 2025-12-22 22:42:48 -08:00
Alison Shao
ac42797cf7 [CI] Enable retry logic for flaky CI tests (#14983) 2025-12-22 22:23:42 -08:00
Alison Shao
883747ced1 [CI] Migrate Attention Backend tests to test/registered/attention/ (#15563) 2025-12-22 22:17:52 -08:00
Alison Shao
989d4b3012 [CI] Migrate nightly tests to test/registered/ (#15582) 2025-12-22 22:16:32 -08:00
Baidu-AIAK
bc3ca30023 [PD] Support fake decode for PD disaggregation without prefill node (#14628)
Co-authored-by: sunhailiang <sunhailiang@baidu.com>
2025-12-23 12:43:33 +08:00
yuchengz816-bot
061f41affc MoE: Skip SiLU/GELU activation for masked experts (#15539)
Co-authored-by: Runkai Tao <rt572@physics.rutgers.edu>
2025-12-22 19:08:31 -08:00
Yuxuan Zhang
82f1d6157f [GLM-ASR] GLM-ASR Support (#15570)
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
2025-12-22 17:37:55 -08:00
Lianmin Zheng
5e1a495c65 Improve engine customization interface (#15635) 2025-12-22 14:24:16 -08:00
sglang-bot
34013d9d5a chore: bump sgl-kernel version to 0.3.20 (#15590)
Co-authored-by: sglang-bot <sglang-bot@users.noreply.github.com>
2025-12-22 12:32:34 -08:00
SeanWeiSean
7759716786 bugfix[schedule]: Refactor sort method and add related UT (#13576)
Co-authored-by: Yuxuan Wei <w1300012920@pku.edu.cn>
Co-authored-by: Yuxuan Wei <w1300012920@gmail.com>
Co-authored-by: Yuxuan Wei🚚 <yuxwei@microsoft.com>
2025-12-23 03:13:57 +08:00
Liangsheng Yin
3c882db3ad Adjust wrong mtp meaning introduce by mimo (#15632)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-12-23 02:06:46 +08:00
fzyzcjy
b736a1525a Tiny add back missing router per attempt response metric (#15621) 2025-12-22 09:59:10 -08:00
fzyzcjy
6984837d82 Fix router gRPC mode launch error caused by async loading (#15368) 2025-12-22 09:39:01 -08:00
Simo Lin
2142881b7e [model-gateway] return 503 when all workers are circuit-broken (#15611) 2025-12-22 04:06:09 -10:00
Xiaoyu Zhang
d77f3fccbf [Diffusion] Support peak memory record in offline generate and serving (#15610) 2025-12-22 21:21:21 +08:00
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