minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity
18,248 Commits 2 Branches 0 Tags
45b511b2efa0faa2ed5893fcd0d9ee61789c1910
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Alison ShaoandClaude Opus 5 00143e9c23 Fix dataclasses.asdict on the msgspec ServerArgs (#38958) 
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
 2026-09-10 17:22:54 -07:00
Alison Shao 2f7393f0d2 [Simulator] Give the OFFLINE/BLOCKING comparison tolerances real headroom (#38732) 2026-09-10 11:10:38 +08:00
Alison Shao 3700c4ee26 [CI] Temporarily disable GB300 tests (#38770) 2026-09-09 18:31:00 -07:00
Alison Shao a7e00b7576 [CI] Answer unrecognized slash commands instead of skipping silently (#38736) 2026-09-09 18:01:18 -07:00
Alison Shao 2948a62a6f [CI] Add /run-full-ci and /run-extra-ci slash commands (#38734) 2026-09-09 13:56:38 -07:00
Alison ShaoandClaude Opus 5 95a88bfd69 Relax GSM8K thresholds for the GLM-5.2 DSA-MTP variants (#38725) 
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
 2026-09-09 12:46:10 -07:00
Alison Shao 76eea36e38 Cast fp32 routing weights to bf16 in the Kimi-K3 fused finalize (#38588) 2026-09-09 10:48:21 +08:00
Alison Shao db1eb48651 [CI] Graceful teardown for the PD and HiSparse server fixtures (#37485) 2026-09-02 17:22:18 -07:00
Alison Shao a6da3a4922 [CI] Re-enable GB300 jobs (#37522) 2026-09-02 16:15:40 -07:00
Alison Shao 23cb11ae01 Fix KV cache pool sized far too small when weight-loading memory is still referenced (#36583) 2026-08-28 09:47:23 -07:00
Alison Shao a126a5fa31 [CI] Graceful teardown for the radix_cache server fixtures (#36605) 2026-08-27 16:36:04 +08:00
Alison Shao 02dfd37826 [CI] Remove GLM-4.1V-9B-Thinking from nightly VLM MMMU eval (#36602) 2026-08-26 20:29:38 -07:00
Alison Shao 15688fea7d Fix BailingMoeV3 reading enable_dp_lm_head off live topology instead of config (#36584) 2026-08-26 18:41:39 -07:00
Alison Shao 3ec22948c1 [CI] /rerun-failed-ci: rerun cancelled runs and target the newest run per workflow (#34057) 2026-08-25 20:15:54 -07:00
Alison Shao 4382947b58 Fix DSV4 shared-fusion CPU unit test after the EP guard landed (#36424) 2026-08-25 19:52:05 -07:00
Alison Shao 0c1e9bda57 [OpenAI] Drop empty assistant turns for mistral_common tokenizers (#35915) 
mistral_common rejects an assistant turn carrying neither content nor tool calls, while other chat templates ignore it, so an OpenAI-compatible request that works elsewhere failed on Mistral models. Drop those turns before templating; turns with tool_calls, multimodal content, or real text are untouched, and a trailing assistant message is already consumed upstream as the continue_final_message prefix.
 2026-08-23 20:07:17 -07:00
Alison Shao 2440820528 docs: add website link to README header (#35210) 2026-08-21 15:50:52 -07:00
Alison ShaoandXinyuan Tong 3391ab3712 [Constrained] Support MistralCommon tokenizers in the XGrammar backend (#35215) 
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
 2026-08-19 12:34:48 +08:00
Alison Shao 0877a0e2f1 [CI] Add speculative_draft_attention_backend to the page-constraint test view (#33254) 2026-08-02 04:58:59 -07:00
Alison Shao 43be25b2b7 [CI] Graceful teardown for kv_canary and EAGLE spec fixtures (#32829) 2026-08-02 01:09:59 -07:00
Alison Shao 301ea43f35 [CI] Re-enable GB300 CI jobs (#32719) 2026-07-31 14:22:26 -07:00
Alison Shao 1b4cb6b8c1 Route /rerun-test for b200 multimodal tests to the b200 pool (#31928) 2026-07-21 16:41:17 -07:00
Alison Shao 696e8f80d1 [CI] Graceful teardown in kl_mamba hicache tests to release pinned host pool (#31871) 2026-07-21 02:09:26 -07:00
Alison Shao 3f48245080 [CI] Temporarily disable GB300 jobs (runner availability) (#31764) 2026-07-20 01:19:24 -07:00
Alison Shao 2f14d6c6f2 ci: run nvidia nightly every 2 days at 14:00 UTC (7am PT) (#31749) 2026-07-19 23:58:39 -07:00
Alison Shao 1a317839d7 ci: lower VL PP gsm8k threshold to 0.60 (0.65 has zero margin on H100) (#31702) 2026-07-19 15:41:12 -07:00
Alison Shao 688a6d23f1 [DeepSeek-V4] Fix idle-rank dummy-extend sparse-prefill crash under DP breakable CUDA graph (#31705) 2026-07-19 14:42:04 -07:00
Alison Shao a5c0b94034 Let CI server launches wait longer for ports held by a dying predecessor (#31281) 2026-07-17 21:45:24 -07:00
Alison Shao e48eabbeee ci: add MLX to coverage report backend display order (#31442) 2026-07-17 17:32:20 -07:00
Alison Shao f926c30c57 Revert "Fix mamba track-boundary seqlen under overlap scheduler (#31369)" (#31622) 2026-07-17 17:03:10 -07:00
Alison Shao 059ac7efe8 Don't fail server startup when psutil can't parse /proc/meminfo (GB300 ShadowCallStack) (#31098) 2026-07-16 14:57:34 -07:00
Alison Shao 238448f4c8 ci: fix runner utilization report undercounting busy time ~25x (#31396) 2026-07-15 22:02:38 -07:00
Alison Shao 21a6d08557 ci: strip invisible Unicode format chars from slash-command input (#31234) 2026-07-14 16:33:45 -07:00
Alison Shao 771e386332 Disable flaky DSV4-Flash FP4 BCG determinism test (nondeterminism from #30898 idle-rank dummy extend) (#31125) 2026-07-14 16:21:10 -07:00
Alison Shao 464fe1b77c [CI] Use torch.testing.assert_close in custom-all-reduce test (~1400x faster compare) (#31080) 2026-07-14 08:53:20 +08:00
Alison Shao 32cb89d412 ci: prune uv cache in job teardown to bound its growth (#30813) 2026-07-11 18:01:23 +08:00
Alison Shao 90688366d9 test(disagg): set MC_GID_INDEX on RoCE hosts so mooncake KV transfer works (#30737) 2026-07-11 11:29:22 +08:00
Alison Shao f3c3eea608 ci: make multi-GPU jit test hangs attributable from the CI log (#29925) 2026-07-07 19:56:32 -07:00
Alison Shao 99db3b0fa5 ci: run jit-kernel tests on scheduled full runs (#30306) 2026-07-07 00:14:39 -07:00
Alison Shao b28bc1060f fix(mimo-vl): pass padded_context_dim to Qwen2_5_VisionPatchMerger (#29994) 2026-07-04 08:08:25 +08:00
Alison ShaoBaizhou ZhangMohammad Miadh Angkad
 		ab0714d0ee ci: run GB300 nightly suite in the standard Nvidia nightly workflow (#28536) 
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
Co-authored-by: Mohammad Miadh Angkad <176301910+mmangkad@users.noreply.github.com>
 2026-06-19 12:24:38 -07:00
Alison Shao f6e6394d86 ci: run pr-test-extra on release branch cuts (not just base suites) (#27627) 2026-06-08 21:18:50 -07:00
Alison Shao 9c53031d2b ci: partition the H200 nightly 'Run test' step across the matrix (#27621) 2026-06-08 20:49:12 -07:00
Alison Shao 0783813fdf ci: cache HF hub for base-a-test-cpu to avoid Hub 429 flakes (#27092) 2026-06-04 04:25:00 -04:00
Alison ShaoandCheng Wan 76c9899da7 Fix hybrid linear attention misrouting plain-RadixAttention linear layers to the full backend (Ring-2.5-1T) (#26623) 
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
 2026-06-02 16:24:49 -07:00
Alison Shao 365cc2ade5 jit_kernel tests: bump multiprocess_test timeout 90s -> 240s (cold JIT cache) (#26994) 2026-06-02 17:33:52 -04:00
Alison Shao 547b886b3c ci: drop redundant multimodal-server jobs from nightly (Nvidia) (#26985) 2026-06-01 23:40:48 -07:00
Alison Shao edfe8d34e8 [CI] ci-coverage-overview: schedule + manual only, include XPU/MUSA/multimodal_gen (#26619) 2026-05-30 16:39:18 +08:00
Alison Shao b4bf489dea ci: allow /rerun-test to dispatch nightly/weekly CUDA tests (#26624) 2026-05-30 16:35:01 +08:00
Alison Shao 0597242797 [CI] /rerun-test: descend into directories that a glob matched (#26614) 2026-05-28 16:52:42 -07:00
Alison Shao 5018e5c969 [CI] /rerun-test: support glob wildcard patterns (#26422) 2026-05-27 21:55:58 -07:00
Alison Shao 7c421ed3ec [CI] runner-utilization: count in-flight queue waits + per-job status/links (#26509) 2026-05-27 16:06:55 -07:00
Alison Shaohnyls2002Liangsheng Yin
 		4adfc6cf7e ci: dispatch pr-test-extra.yml from pr-test.yml on the scheduled cron (#25320) 
Co-authored-by: hnyls2002 <lsyincs@gmail.com>
Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
 2026-05-15 01:01:23 -07:00
Alison Shaohnyls2002Liangsheng Yin
 		ba214ef3d3 ci: tag-gated nightly migration — foundation + 40 whole-file moves (#24725) 
Co-authored-by: hnyls2002 <lsyincs@gmail.com>
Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
 2026-05-14 16:11:15 -07:00
Alison Shao 36c9495aaa ci: H200 conditional split + dsv4 est_time recalibration (h200 partition 6→2) (#25236) 2026-05-13 22:28:37 -07:00
Alison Shao b71d74673c ci: combine H200 8-GPU warmup steps and surface server log on every path (#24253) 2026-05-13 20:09:52 -07:00
Alison Shao 1e308aec66 ci: B200 conditional split + LPT_SLOP removal (stage-c partition 8→3) (#25203) 2026-05-13 18:40:45 -07:00
Alison Shao dd98153d17 chore(ci_monitor): drop post_bisect_to_slack (#25192) 2026-05-13 17:05:38 -07:00
Alison Shao 1419bcc39e [CI] Temporarily disable multimodal-gen test_update_weights_from_disk (flaky) (#25032) 2026-05-12 12:28:33 -07:00
Alison Shao 5fbec0e445 ci: prune per-commit CUDA tests — move 25 files + 13 testcases to test/manual/ (#24721) 2026-05-08 15:53:23 -07:00
Alison Shao aefd8e257f Re-land #23109: rebase-required mode + fix for grep-no-match abort (#24180) 2026-05-08 15:28:57 -07:00
Alison Shao e72246c6e6 ci: bump test_mimo_models.py est_time 330 → 610 (#24551) 2026-05-06 14:35:43 -07:00
Alison Shao 094b90b1ec ci: drop 1-gpu-h100-h200 shared label (#24495) 2026-05-06 01:02:31 -07:00
Alison Shao f3dbadb82b fix: accept 0-indexed safetensors shard names in CI weight validator (#24237) 2026-05-02 00:58:15 -07:00
Alison Shao 357e3789ea ci: limit nightly test parallelism to 1 job per hardware type (#23314) 2026-04-30 21:49:18 -07:00
Alison Shao 918f910cf0 ci: temporarily disable multimodal-gen-test-1-b200 (#24174) 2026-04-30 16:16:43 -07:00
Alison ShaoandAlison Shao 694ef516cb Revert "[ci] split stage-c-test-4-gpu-b200 to enable a low-disk runner pool" (#24163) 
Co-authored-by: Alison Shao <alisonshao@radixark.ai>
 2026-04-30 15:57:19 -07:00
Alison ShaoandAlison Shao cdc4078815 ci: add rebase-required mode to check-maintenance action (#23109) 
Co-authored-by: Alison Shao <alisonshao@radixark.ai>
 2026-04-30 15:47:24 -07:00
Alison Shao dc395bc059 ci: run setup_ld_library_path before install_sglang_kernel (#24141) 2026-04-30 10:55:45 -07:00
Alison Shao 7bb7f6049a ci: add per-host utilization view to runner-utilization report (#24102) 2026-04-30 10:05:16 -07:00
Alison Shao b73c44b545 test: relax TestMLADeepseekV3.test_gsm8k threshold 0.62 -> 0.60 (#23879) 2026-04-27 15:27:15 -07:00
Alison Shao 267c2c0849 test: move test_epd_disaggregation to nightly-4-gpu (#23518) 2026-04-22 20:59:19 -07:00
Alison Shao 04b1caf75b ci: enable /rerun-test for multimodal gen PR tests (#22828) 2026-04-21 21:34:14 -07:00
Alison Shao 0e165ffbfc ci: enable /rerun-test for nightly test suites (#22830) 2026-04-21 18:28:10 -07:00
Alison Shao 6b19e8a452 ci: reduce scheduled PR test from 4x to 3x daily (#23313) 2026-04-20 20:53:13 -07:00
Alison Shao 0052093178 test(4-gpu-b200): split test_qwen35_models.py + bump partitions 5→6 (#22913) 2026-04-16 18:51:59 -07:00
Alison Shao 3f4fbc165d Upgrade CI default CUDA version from 12.9 to 13.0 (#21441) 2026-04-12 21:48:40 -07:00
Alison ShaoandAlison Shao d6c9d9116b [CI] Update B200 est_times to prevent timeouts on slower machine (#22609) 
Co-authored-by: Alison Shao <alison.shao@MacBook-Pro-D2W773R9CD.local>
 2026-04-11 21:40:34 -07:00
Alison ShaoandAlison Shao f21d23a211 ci: use local NVIDIA wheels to avoid re-downloading ~2GB every CI run (#22602) 
Co-authored-by: Alison Shao <alison.shao@MacBook-Pro-D2W773R9CD.local>
 2026-04-11 21:32:51 -07:00
Alison ShaoandAlison Shao 870a21bf39 [CI] Remove Slack bot from CI failure monitor (#21581) 
Co-authored-by: Alison Shao <alison.shao@Mac.attlocal.net>
 2026-04-11 20:34:48 -07:00
Alison ShaoandAlison Shao 75223c5404 [Diffusion][CI] Fix nunchaku unit test broken by #22365 (#22560) 
Co-authored-by: Alison Shao <alison.shao@MacBook-Pro-D2W773R9CD.local>
 2026-04-10 17:49:56 -07:00
Alison ShaoandAlison Shao b853e2c41b [CI] Remove Slack notification from ci-auto-bisect workflow (#22483) 
Co-authored-by: Alison Shao <alison.shao@Mac.lan>
 2026-04-09 20:32:09 -07:00
Alison ShaoAlison ShaoAlison Shao
 		45b0182205 [CI] Update est_time for 64 tests based on actual elapsed times (#22305) 
Co-authored-by: Alison Shao <alison.shao@Mac.lan>
Co-authored-by: Alison Shao <alison.shao@MacBook-Pro-D2W773R9CD.local>
 2026-04-09 20:31:37 -07:00
Alison ShaoandAlison Shao cf27b11498 [CI] Increase stage-c-test-4-gpu-b200 partitions from 4 to 5 (#22395) 
Co-authored-by: Alison Shao <alison.shao@MacBook-Pro-D2W773R9CD.local>
 2026-04-08 16:36:27 -07:00
Alison ShaoandAlison Shao 614dd1d4f5 [CI] Add alexnails to CI_PERMISSIONS.json (#22391) 
Co-authored-by: Alison Shao <alison.shao@MacBook-Pro-D2W773R9CD.local>
 2026-04-08 16:22:05 -07:00
Alison ShaoAlison ShaoAlison Shao
 		e41647f52b [CI] Add pre-commit hook to validate test/registered/ files have CI registry (#22308) 
Co-authored-by: Alison Shao <alison.shao@Mac.attlocal.net>
Co-authored-by: Alison Shao <alison.shao@MacBook-Pro-D2W773R9CD.local>
 2026-04-08 15:59:15 -07:00
Alison ShaoandAlison Shao 2ad5e6df12 [CI] Relax gpt-oss 4GPU accuracy threshold from 0.60 to 0.58 (#22237) 
Co-authored-by: Alison Shao <alison.shao@Mac.attlocal.net>
 2026-04-08 02:20:23 -07:00
Alison ShaoandAlison Shao 36f05810c9 [CI] Move manual-only nightly tests out of test/registered/ (#22298) 
Co-authored-by: Alison Shao <alison.shao@Mac.attlocal.net>
 2026-04-07 21:03:52 -07:00
Alison ShaoandAlison Shao 86e4542f35 Use dedicated runner label for deepep 8-GPU tests (#22309) 
Co-authored-by: Alison Shao <alison.shao@Mac.attlocal.net>
 2026-04-07 19:58:54 -07:00
Alison ShaoandAlison Shao 6f1412f4f5 [CI] Relax transformers MMLU threshold from 0.65 to 0.64 (#22210) 
Co-authored-by: Alison Shao <alison.shao@Mac.attlocal.net>
 2026-04-06 15:32:09 -07:00
Alison ShaoandAlison Shao 1ac74e652e [Misc] Fix comparator e2e tests: add polars dep + fix dp-attention test (#21804) 
Co-authored-by: Alison Shao <alison.shao@mac.lan>
 2026-04-01 15:44:35 -07:00
Alison ShaoandAlison Shao 9b6bee2d40 Fix human-eval CI install on 5090 runners (#21714) 
Co-authored-by: Alison Shao <alison.shao@Mac.attlocal.net>
 2026-03-30 18:53:09 -07:00
Alison ShaoandAlison Shao 3650bfb199 Remove flashinfer wheel cache cleanup that deletes other versions (#21711) 
Co-authored-by: Alison Shao <alison.shao@MacBook-Pro-D2W773R9CD.local>
 2026-03-30 16:47:04 -07:00
Alison ShaoAlison ShaoAlison Shaohnyls2002Liangsheng Yin
 		5297a3cb46 [CI] Rewrite killall_sglang as Python with CI/local dual mode (#21331) 
Co-authored-by: Alison Shao <alison.shao@mac.lan>
Co-authored-by: Alison Shao <alison.shao@MacBook-Pro-D2W773R9CD.local>
Co-authored-by: hnyls2002 <lsyincs@gmail.com>
Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
 2026-03-24 23:54:01 -07:00
Alison ShaoAlison Shaohnyls2002
 		17e41cfb21 Fix RDMA device mapping for non-zero GPU indices in disaggregation tests (#21303) 
Co-authored-by: Alison Shao <alison.shao@MacBook-Pro-D2W773R9CD.local>
Co-authored-by: hnyls2002 <lsyincs@gmail.com>
 2026-03-24 22:56:57 -07:00
Alison ShaoandAlison Shao 44db0c59cf [CI] Fix cutlass import error: restore nvidia-cutlass-dsl force-reinstall (#21182) 
Co-authored-by: Alison Shao <alison.shao@mac.lan>
 2026-03-22 22:41:01 -07:00
Alison ShaoandAlison Shao 852e112ebf [Qwen3.5] Fix broken pipeline parallelism layer splitting (#21070) 
Co-authored-by: Alison Shao <alison.shao@Mac.attlocal.net>
 2026-03-21 01:02:51 -07:00
Alison ShaoandAlison Shao b7a1ae4fac Fix /rerun-stage dispatch failure for non-AMD stages (#21076) 
Co-authored-by: Alison Shao <alison.shao@Mac.attlocal.net>
 2026-03-20 23:48:29 -07:00
Alison Shao 048d90e165 Revert "[AMD] Add MoE weights and scales padding" (#21067) 2026-03-20 20:26:17 -07:00
Alison ShaoandAlison Shao 7b44bc923e Relax flaky B200 GSM8K accuracy thresholds (#20304) 
Co-authored-by: Alison Shao <alisonshao@Mac.attlocal.net>
 2026-03-11 12:35:21 -07:00