Commit Graph

8620 Commits

Author SHA1 Message Date
Alison Shao
399d5283f8 ci: migrate scheduler tests to test/registered/scheduler/ (#16442) 2026-01-06 14:55:52 -08:00
Alison Shao
2e0527dd74 ci: migrate Debug Utils, Ops, and Rotary Embedding tests to test/registered/ (#16422) 2026-01-06 14:35:57 -08:00
Yingchun Lai
6beb50d612 feat: add .dockerignore to ignore files when build images (#16223) 2026-01-06 14:34:16 -08:00
Kangyan-Zhou
18e2ef09d7 Add v1/models endpoint to diffusion model APIs so that they can be discovered by model gateway (#16425) 2026-01-06 14:28:24 -08:00
Alison Shao
3271e0e76d Remove dllm-test-1-gpu-amd job (followup to DLLM migration) (#16589) 2026-01-06 14:27:37 -08:00
Simo Lin
d415d22daa refactor(e2e): remove old embedding tests migrated to e2e_test/embeddings (#16592) 2026-01-06 14:07:45 -08:00
Simo Lin
a49b9a6420 [model-gateway] add embedding tests (#16583) 2026-01-06 13:24:37 -08:00
Douglas Yang
5349764298 fix: kimi k2 thinking accuracy threshold change (#16585) 2026-01-06 13:18:43 -08:00
Simo Lin
d57d8e7e5f [smg] clean up logs in mcp (should be info instead warn) (#16591) 2026-01-06 12:44:32 -08:00
Alison Shao
0cbd8f3247 ci(test): migrate OpenAI server tests to registered CI system (#16326)
Co-authored-by: Kangyan-Zhou <zky314343421@gmail.com>
2026-01-06 11:09:37 -08:00
Douglas Yang
6e3fff1352 fix: adding retries for server start and increasing hf read timeout (#16523) 2026-01-06 09:53:12 -08:00
Alison Shao
2210155a45 ci: migrate DLLM tests to test/registered/dllm/ (#16420) 2026-01-06 09:44:26 -08:00
Simo Lin
a3656cbb96 [ci] fix url strips in smg ci (#16548)
Co-authored-by: Chang Su <chang.s.su@oracle.com>
2026-01-06 09:23:58 -08:00
Chang Su
21da2dc1ce [grpc] Unify ResponsesContext and HarmonyResponsesContext (#16549) 2026-01-06 07:28:06 -08:00
fzyzcjy
ed307a40bf Tiny add --gsp-ordered (#16575) 2026-01-06 22:43:52 +08:00
Ke Bao
02722b9113 Fix evict swa for overlap scheduler and page size > 1 (#16507) 2026-01-06 22:29:40 +08:00
fzyzcjy
f959250f76 Tiny support sglang_routing_keys_active in engine (#16570) 2026-01-06 22:10:10 +08:00
YAMY
959343795f [test] update acc len threshold to 2.7 for eagle dp attention tests (#16463) 2026-01-06 17:38:35 +08:00
Junrong Lin
bc2f40bebc [test] Add mamba cache release/resume memory test (#14215) 2026-01-06 15:51:10 +08:00
lw9527
2724b1100b fix double Unicode escape issue in streaming tool_calls parameters (#13518)
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
2026-01-05 23:47:26 -08:00
Alison Shao
176266f358 Migrate sampling tests to test/registered/sampling/ (#16455) 2026-01-05 23:43:20 -08:00
Xiaoyu Zhang
5e5b1183ed [Diffusion] Ring Attention support sage backend (#16496) 2026-01-06 14:45:53 +08:00
Chang Su
9bf76c11a9 [responses API] Add list_tools_for_servers and threading server_keys in routers (#16540) 2026-01-05 22:42:22 -08:00
jiapingW
1d7ad4afcc [diffusion] fix: fix bench_serving always use prompt fixed prompts (#16201)
Co-authored-by: jiapingW <root@sgl-training-ray.datacrunch.io>
Co-authored-by: Mick <mickjagger19@icloud.com>
2026-01-06 14:39:07 +08:00
siyu
fba785c459 use aync load for encoder_server (#15456)
Signed-off-by: liuanqi <liuanqi6@xiaomi.com>
Co-authored-by: Yuhao Yang <47235274+yhyang201@users.noreply.github.com>
Co-authored-by: liuanqi <liuanqi6@xiaomi.com>
2026-01-06 14:31:52 +08:00
Alison Shao
5cfa901b57 ci: migrate Constrained Decoding tests to test/registered/constrained/ (#16421) 2026-01-05 22:29:22 -08:00
Alison Shao
f27c6cdc2b Migrate metrics tests to test/registered/metrics/ (#16466) 2026-01-05 22:21:49 -08:00
Douglas Yang
5097e1e85b fix: moving dpsk v32 cp single node to nightly (#16539) 2026-01-05 22:18:59 -08:00
Alison Shao
861a35fb6e ci: migrate RL tests to test/registered/rl/ (#16417) 2026-01-05 22:13:13 -08:00
Baizhou Zhang
6ffe1fc02f [Fix]Pin mooncake version to 0.3.7.post2 in grace blackwell (#16502) 2026-01-06 14:11:40 +08:00
Alison Shao
73398e22d6 ci: migrate VLM tests to test/registered/vlm/ (#16415) 2026-01-05 21:25:29 -08:00
Alison Shao
17958c5f0d Migrate parsing tests to test/registered/parser/ (#16467) 2026-01-05 21:15:32 -08:00
Ke Bao
3aa11ca722 Remove hybrid_kvcache_ratio in server args (#16399) 2026-01-06 13:13:13 +08:00
Adarsh Shirawalmath
7be1a8c70c [diffusion] feat: support diffusers backend - run any model supported by diffusers (#14112) 2026-01-06 12:30:57 +08:00
Raayan Dhar
84d13c54bb feat: only add input vision tokens in bench_serving result if vision dataset is used (#15492)
Signed-off-by: Raayan Dhar raayan.dhar@gmail.com <raayan.dhar@gmail.com>
2026-01-06 12:14:42 +08:00
Douglas Yang
c80c0e0fc0 fix: adding multi-threading for kimi weights loading in pr test (#16538) 2026-01-05 20:10:13 -08:00
fzyzcjy
c105a3124b Support multi-round conversations in bench_serving (#6135) 2026-01-06 11:59:39 +08:00
Chang Su
4cf2bbd084 [router] Remove deadcode and add note for unused API completeness methods (#16528) 2026-01-05 19:53:28 -08:00
Alison Shao
d7b706be94 ci: migrate HiCache 1-GPU tests to test/registered/hicache/ (#16416) 2026-01-05 19:38:21 -08:00
Alison Shao
4a9537a495 ci: migrate Mamba/Layers tests to test/registered/layers/mamba/ (#16419) 2026-01-05 19:12:47 -08:00
Mick
ca922d4b05 [diffusion] feat: support warmup with resolutions (#16434) 2026-01-06 10:32:18 +08:00
Simo Lin
402a0bd6dc [model-gateway] Add model scope support and LRU eviction for GPU-constrained environments (#16525) 2026-01-05 18:28:07 -08:00
Douglas Yang
76c71d1d34 fix: unimplemented methods in BaseIndexerMetadata (#16520) 2026-01-06 10:26:42 +08:00
zhangheng
2d02c150dc [3/N][Sparse With Hicache]: Init sparse coordinator (#16086)
Co-authored-by: 晟海 <huangtingwei.htw@antgroup.com>
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
2026-01-05 17:51:04 -08:00
Chang Su
b98bd9a5fb [model-gateway] Tighten visibility in modules and remove unused re-exports (#16524) 2026-01-05 17:38:50 -08:00
ShirakSyouya
ce694b2b9e Fix the problem where Qwen3VL raises an "object has no attribute 'mod… (#15677) 2026-01-06 08:45:13 +08:00
Lianmin Zheng
6c0fb189f8 [Auto Sync] Update tokenizer_manager.py (20260105) (#16477)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Wangfan Fu <wangfan@x.ai>
2026-01-05 14:06:03 -08:00
Binyao Jiang
9a9f996f8d [FP8] Fix weight_scale shape to match with x_scale shape for per-tensor quant under torch.compile (#16356) 2026-01-05 13:55:26 -08:00
Simo Lin
4221b7c573 [model-gateway] refactor e2e test infrastructure and add router CI (#16513) 2026-01-05 13:50:59 -08:00
yctseng0211
c371df2f25 [AMD] Fix CI and add retry logic for git clone timeout (#15663)
Co-authored-by: Bingxu Chen <bingxche@amd.com>
2026-01-05 12:37:52 -08:00