 Jiajun Li
|
919a6502fe
|
ci(wheels): notify Lark when builds or publishing fail (#3881)
|
2026-10-01 15:32:18 -07:00 |
|
|
Jiajun LiandClaude Opus 5.5
|
1f92079cfc
|
ci(wheels): add a workflow that rebuilds the x86_64 TE wheels from the fork (#3871)
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-01 15:23:36 -07:00 |
|
|
Jiajun Li
|
957e11642f
|
fix(ci): preserve image cuDNN during dependency resolution (#3880)
|
2026-10-01 15:22:28 -07:00 |
|
|
Jiajun LiandClaude Opus 5.5
|
f84b1496e1
|
test(e2e): move 8x H100 e2e tests to H200 stages and widen parallelism coverage (#3660)
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-09-27 20:41:43 -07:00 |
|
|
fzyzcjy
|
cee2e4b143
|
Cover the ray x rpc worker comm path in CI (#3048)
|
2026-09-26 20:32:29 +08:00 |
|
|
fzyzcjy
|
1a2a72a3e2
|
Compare a run deployed in parts against the same run deployed as one (#3006)
|
2026-09-26 20:11:12 +08:00 |
|
|
fzyzcjy
|
8a12b98547
|
Add a solver-verifier example on gsm8k (#2645)
|
2026-09-26 19:08:04 +08:00 |
|
|
Yueming Yuan
|
3d01116aee
|
release: gate on CPU and CUDA CI only (#3705)
|
2026-09-25 18:40:18 -06:00 |
|
|
Yueming Yuan
|
41c5e38b94
|
release: grant permissions required by nested CI (#3704)
|
2026-09-25 01:44:28 -07:00 |
|
|
Yueming Yuan
|
9e5cfd143a
|
release: publish CUDA 13 only and fingerprint configured wheels (#3703)
|
2026-09-25 01:37:23 -07:00 |
|
|
Xinyu JiangandZhiyao Jiang
|
e30b8b6dd6
|
[AMD] replace the ROCm 7.2.0 image with ROCm 7.2.4 (#3326)
Co-authored-by: Zhiyao Jiang <jessicajiang324@gmail.com>
|
2026-09-24 03:59:24 -04:00 |
|
|
Jiajun Li
|
84ebad0569
|
ci(docker): notify Lark when an automatic image build fails (#3639)
|
2026-09-23 15:33:32 -07:00 |
|
|
Jiajun Li
|
d2b66cab68
|
ci(docker): poll upstream every 10 minutes and rebuild at least every 12h (#3630)
|
2026-09-23 15:29:41 -07:00 |
|
|
Jiajun Li
|
8b4d79bf50
|
ci: run PR Test on non-main-base PRs only with a run-ci label (#3636)
|
2026-09-23 15:27:23 -07:00 |
|
|
Jiajun Li
|
a28af4e91d
|
feat(ci): grant label commands permission (#3126)
|
2026-09-22 22:15:17 -07:00 |
|
|
Alison Shao
|
8ddaf55b02
|
ci: daily runner utilization report with queue-wait percentiles (#3586)
|
2026-09-21 17:48:37 -07:00 |
|
|
Yueming Yuan
|
a66064f190
|
fix(ci): install test dependencies before training pins (#3580)
|
2026-09-21 17:08:17 -07:00 |
|
|
Yueming Yuan
|
f6d0257d83
|
[multi-lora v2 7/7] Tinker gateway example and tests
|
2026-09-16 01:26:14 -07:00 |
|
|
Yueming Yuan
|
c2f43c7310
|
ci(lark): rerun failed nightly jobs once and report flaky vs failed (#3251)
|
2026-09-14 16:23:16 -07:00 |
|
|
Jiajun Li
|
7c48f1cc7e
|
fix(ci): build fork PR images through trusted orchestration (#3235)
|
2026-09-14 15:04:08 -07:00 |
|
|
Jiajun Li
|
4bff43b01b
|
fix(ci): prepare PR images only for selected GPU tests (#3234)
|
2026-09-14 15:04:08 -07:00 |
|
|
Yueming Yuan
|
3ccc2cb37e
|
ci(lark): give each failure block room in the evidence packet (#3212)
|
2026-09-11 16:39:31 -07:00 |
|
|
Yueming Yuan
|
2f9bb0248b
|
ci(lark): collapse jobs that failed identically into one card row (#3197)
|
2026-09-10 12:14:58 -07:00 |
|
|
Yueming Yuan
|
ac1231a54f
|
fix(ci): stop a CPU failure from skipping the GPU stages a nightly asked for (#3196)
|
2026-09-10 12:14:49 -07:00 |
|
|
Yueming YuanandJiajun Li
|
63995c221e
|
feat(ci): dispatch a CI run to a GPU generation (#2703)
Co-authored-by: Jiajun Li <guapisolo@gmail.com>
|
2026-09-09 22:00:54 -07:00 |
|
|
Tao LinandClaude Fable 5
|
0cdaaaf83b
|
ci(e2e): Harbor trials on real e2b sandboxes through the full rollout path (manual for now) (#2876)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-09-09 23:23:24 -04:00 |
|
|
Yueming Yuan
|
fa7939f899
|
ci(lark): report every failing test in a job (#3168)
|
2026-09-09 15:17:32 -07:00 |
|
|
Yueming YuanandAlan Livshin
|
327eefa0fb
|
ci(lark): explain each failed job on the CI status card (#3152)
Co-authored-by: Alan Livshin <alan.livshin@alivshin-mbp.tail134ba0.ts.net>
|
2026-09-09 11:31:52 -07:00 |
|
|
Xinyu JiangandZhiyao Jiang
|
8d9826eacc
|
[AMD] docker: retire the rocm700 variants, add a rocm10-mi35x variant (#2854)
Co-authored-by: Zhiyao Jiang <jessicajiang324@gmail.com>
|
2026-09-08 22:37:39 -07:00 |
|
|
Jiajun Li
|
78747f6912
|
refactor(docs): nest CI pages under developer (#3134)
|
2026-09-06 23:25:38 -07:00 |
|
|
Yueming Yuan
|
8d60ec7dbc
|
ci: add Lark status notifications (#3101)
|
2026-09-03 17:44:20 -07:00 |
|
|
Jiajun Li
|
1e3b7a0887
|
fix(ci): mint the command-App token with pull-requests: write for label commands (#2877)
|
2026-09-01 23:33:19 -07:00 |
|
|
Jiajun Li
|
6d068bafb2
|
feat(ci): add user allowlists for command tiers (#2813)
|
2026-08-30 20:33:58 -07:00 |
|
|
Yueming Yuan
|
ca25d697c0
|
feat(ci): add stage-c-8-gpu-b200 for the Blackwell runner (#2700)
|
2026-08-29 23:37:22 -07:00 |
|
|
MichaelandCursor Agent
|
7df95c3c16
|
[AMD] fix(docker): drop the obsolete ROCm Megatron fused-kernels patch (#2768)
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
|
2026-08-27 15:12:50 -07:00 |
|
|
|
cd464a1c4c
|
Bump sglang to v0.5.18 (#2714)
Co-authored-by: Zhichen Zeng <zhichen.zeng@radixark.ai>
Co-authored-by: Zhichenzzz <zczeng@uw.edu>
|
2026-08-27 01:08:34 -07:00 |
|
|
Yueming Yuan
|
43a49a08ef
|
ci: default a file run to the PR's own image (#2773)
|
2026-08-26 17:51:31 -07:00 |
|
|
Jiajun Li
|
dfb4dfac3c
|
fix(ci): grant pull-requests write to comment-gateway feedback jobs (#2720)
|
2026-08-23 12:27:24 -07:00 |
|
|
Jiajun Li
|
b66cb4e076
|
fix(ci): App-free rerun commands at contributor tier, with fork /rerun-test under label approval (#2718)
|
2026-08-23 02:16:40 -07:00 |
|
|
fzyzcjyandguapisolo
|
778227d6d7
|
[AMD] Let the ROCm suite honour the ci-sglang-pr and ci-megatron-pr directives (#2674)
Co-authored-by: guapisolo <guapisolo@gmail.com>
|
2026-08-21 00:13:57 -07:00 |
|
|
Jiajun Li
|
819ba9650e
|
feat(ci): acknowledge rerun-test commands (#2676)
|
2026-08-20 21:34:54 -07:00 |
|
|
Yueming Yuanandguapisolo
|
d6cc9672b9
|
[CI] rebuild a PR's docker image only when its build inputs change (#2675)
Co-authored-by: guapisolo <guapisolo@gmail.com>
|
2026-08-20 15:44:40 -07:00 |
|
|
Xinyu Kang
|
597375f315
|
[AMD] Enable four CI tests on ROCm (#2671)
|
2026-08-20 14:05:17 -07:00 |
|
|
Jiajun LiandClaude Fable 5
|
05c94552ef
|
feat(ci): run one test file from a PR comment (#2652)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-08-19 23:45:59 -07:00 |
|
|
Jiajun Li
|
98b285ed26
|
feat(ci): add authorized comment-to-label gateway (#2496)
|
2026-08-19 23:45:59 -07:00 |
|
|
Jiajun Li
|
95a7893615
|
fix(ci): honor nightly fast-fail bypass (#2584)
|
2026-08-17 12:31:02 -07:00 |
|
|
Jiajun Li
|
4e9f36bc7d
|
refactor(ci): require domain labels for GPU tests (#2548)
|
2026-08-16 22:36:29 -07:00 |
|
|
Jiajun Li
|
438ff8c8bc
|
refactor(ci): select GPU stages from PR impact (#2530)
|
2026-08-16 22:36:29 -07:00 |
|
|
Jiajun Li
|
477f136453
|
refactor(ci): gate PR image builds on CPU tests (#2529)
|
2026-08-16 22:36:28 -07:00 |
|
|
|
3547e67d3e
|
release: miles version release workflow (#2538)
Co-authored-by: Jiajun Li <jiajun.li@radixark.ai>
Co-authored-by: guapisolo <guapisolo@gmail.com>
|
2026-08-14 19:57:37 -07:00 |
|