Commit Graph

203 Commits

Author SHA1 Message Date
YuBaoku fdd12ff5ba [CI] Fix: incorrect downstream job execution when only build_gpu/xpu is skipped (#6958)
* [CI] Fix: incorrect downstream job execution when only build_gpu/xpu is skipped

* [CI] Fix: avoid skipping required jobs by moving skip logic to steps

* [CI] Fix: Invalid secret, github-token is not defined
2026-03-22 17:00:18 +08:00
YuBaoku 030820db4c [CI] Optimize CI: refine check-bypass/cancel logic and fix nightly task (#6939)
* [CI] Optimize CI: add check-bypass for workflow skip control

* fix ci_image_build and publish_job

* [CI] Optimize CI: add check-bypass and cancel

* [CI] update to PFCCLab/ci-bypass@v2
2026-03-20 19:34:45 +08:00
YuBaoku 7141db0e01 [CI] Optimize CI: update nightly test_image build workflow (#6937) 2026-03-19 17:39:01 +08:00
YuBaoku 2b84a4276e [CI] Optimize CI: add timeout and cancel on PR close (#6933) 2026-03-19 15:54:30 +08:00
jc dd55cda3c8 [CI] Add test for pd and cache storage (#6876)
* Add test for pd and cache storage

* up

* up

* fix bug

* fix bug

* up docker image

* up
2026-03-19 10:38:27 +08:00
YuBaoku 07543685ec [CI] Isolate cache and ccache for CUDA 13.0 build 2026-03-18 11:41:46 +08:00
YuBaoku d73fd876ba [CI] Add daily build_linux jobs for CUDA 13.0 (#6809) 2026-03-12 22:04:58 +08:00
YuBaoku ab0eacb1ab [CI] Update _build_linux_rl.yml to use Paddle installation method with URL 2026-03-12 20:37:51 +08:00
yzwu 901b38c936 [Iluvatar] Optimize decode group_gemm and Support cuda graph for ernie (#6803) 2026-03-12 19:21:17 +08:00
fxyfxy777 250ce40b40 [Feature] use phi permute/unpermute & rm swiglu (#6361)
* tp文字输出正常

* B eb5 mini文字输出正常

* eb5mini ep B卡 文字输出正常

* default use phi moe op

* stash

* tp H卡正常

* ep ok

* rm debug

* rm debug tool

* rm del ffn_out

* rm swiglu

* add envs to swiglu

* merge dev

* fix ci baseline

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix ci baseline 2

---------

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-12 02:01:57 -07:00
YuBaoku deff121a5f [CI] Update _build_linux_rl.yml to use cu129 nighlty 2026-03-11 23:58:07 +08:00
Jiaxin Sui 25c479312d [CI][MetaX]Add timeout to Jenkins job trigger step (#6755) 2026-03-10 14:26:26 +08:00
YuBaoku cbfdf42628 [CI] Add test_dynamic_c8_cache.py and latest FastDeploy.tar.gz upload (#6708) 2026-03-08 16:01:12 +08:00
Jiaxin Sui 63414ccc13 [XPU][CI] Fix XPU CI Bug (#6658)
* Simplify dependency installation in workflow

Removed triton installation and uninstallation steps.

* Simplify dependency installation in workflow

Removed triton package installation and uninstallation steps.

* Allow docker pull to continue on failure

* Update docker pull command to continue on error

Modify docker pull command to avoid failure on error.

* Allow docker pull to fail without error
2026-03-05 11:27:11 +08:00
YuBaoku 5c8f5184d9 [CI] Add pytest timeout and enable workflow rerun (#6645) 2026-03-04 21:30:16 +08:00
YuBaoku c3d6d706d5 [CI] Add nightly workflow for golang_router tests and improve log handling (#6608)
* [CI] Add nightly workflow for Golang router tests
* [CI] Improve pytest script stability and log handling
2026-03-03 19:36:57 +08:00
YuBaoku 9d72332aca [CI] Optimize unittest and fix title format (#6464)
* [CI] Optimize unit test duration and fix PR title format
2026-02-11 20:48:56 +08:00
Jiaxin Sui e40fb16912 Revert "[XPU] change base XPU docker image (#6411)" (#6427)
This reverts commit 32bd40a192.
2026-02-11 16:31:54 +08:00
kesmeey e4e3a71e7b [CI] 【Hackathon 10th Spring No.22】功能模块 fastdeploy/cache_manager/cache_transfer_manager.py 单测补充 (#6157)
* Add comprehensive test coverage for cache_transfer_manager.py

* Fix code style: add newline at end of file

* fix: update cache transfer manager tests for branch 22 interface changes

* fix: resolve test errors for cache transfer manager

* fix: update cache transfer manager tests for branch 22 interface changes

* style: apply pre-commit formatting to tests/cache_manager/test_cache_transfer_manager.py

* Run codestyle: format tests/cache_manager/test_cache_transfer_manager.py and related fixes

* Update test_cache_transfer_manager.py

* Format cache transfer manager tests

* Update cache transfer manager tests

* Update unit test coverage workflow

---------

Co-authored-by: CSWYF3634076 <wangyafeng@baidu.com>
2026-02-11 11:23:57 +08:00
YuBaoku 390d0f2d77 [CI] Fix cherry-pick automation (#6448)
* [CI] Fix cherry-pick automation
2026-02-10 22:45:29 +08:00
YuBaoku a918738b8f [CI] Optimize cherry-pick automation (#6445) 2026-02-10 21:48:13 +08:00
YuBaoku b84056fdaa [CI] Fix stable_test and add cherry-pick automation (#6415) 2026-02-09 23:10:12 +08:00
Lucas 32bd40a192 [XPU] change base XPU docker image (#6411) 2026-02-09 22:53:12 +08:00
YuBaoku 5c9bc13a59 [CI] Fix check-bypass.yml 2026-02-05 18:06:39 +08:00
YuBaoku 2d3fb81d29 [CI] Update check-bypass.yml (#6360) 2026-02-05 15:52:30 +08:00
YuBaoku cae2709eff [CI] Update stable test workflow and run.sh script (#6352) 2026-02-05 11:01:15 +08:00
Zhang Yulong f3c12be4d2 Update _build_linux_rl.yml (#6274) 2026-01-29 19:10:47 +08:00
YuBaoku bb7c1d13e1 [CI] Remove --ipc=host and --pid=host from _stable_test.yml (#6270) 2026-01-29 17:06:06 +08:00
YuBaoku b07b76e03f [CI] Fix nightly cu129 build_outputs upload failure (#6264) 2026-01-28 23:39:39 +08:00
YuBaoku 85db063da6 [CI] Fix workflow validation error in publish_job 2026-01-28 10:44:30 +08:00
YuBaoku 029cceec33 [CI] Switch nightly build to use FD_UNIFY_BUILD (#6246)
* [CI] Adapt build script for unified and arch-specific builds

* [CI] Switch nightly build to use FD_UNIFY_BUILD
2026-01-27 23:53:42 +08:00
YuBaoku d975f6acdd [CI] adjust resource scheduling of _stable_test (#6235) 2026-01-27 22:31:13 +08:00
Divano ba9d2a9e5a [CI] add update weights tests (#6242) 2026-01-27 20:54:21 +08:00
YuBaoku 1cfb042045 [CI] Add ep4_mtp e2e test (#6153)
* [CI] Add ep4_mtp e2e test
2026-01-22 14:54:18 +08:00
YuBaoku fe5ba4b509 [CI] Update image used by build_rl in ce_job.yml 2026-01-21 20:57:50 +08:00
yzwu 837ddca273 [Iluvartar][CI] Fix the error max_tokens_per_expert referenced before assignment (#6083) 2026-01-21 16:01:29 +08:00
YuBaoku c991fda54c [CI] Enable 4-GPU e2e test in nightly and fix docker_tag_build (#6128) 2026-01-20 22:44:29 +08:00
YuBaoku ac6fa6d725 [CI] Add 4-GPU e2e test job (#6082) 2026-01-19 10:42:14 +08:00
Jiaxin Sui 70a962df53 [XPU][CI] XPU CI refactor (#6053)
* add xpu ci case

* add xpu ci case

* add xpu ci case

* Change runner from XPU-P800-8Card to XPU-P800
2026-01-16 20:57:58 +08:00
MingkunZhang 0d372e4fb2 [Metax][CI] update jenkins github action version (#6065) 2026-01-16 15:06:14 +08:00
fxyfxy777 4c92035f2d [Feature] Unify fp8 block_wise quant ops (#5991)
* quant stash

* blockwise_quant

* precommit

* rm tensor.cut

* tp ok

* add swiglu

* rm outdate code

* fix activate ut

* change baseline

* fix baseline error
2026-01-15 05:50:37 -08:00
YuBaoku 0d3dede273 [CI] Add fd-router build_task (#5967)
* [CI] Add fd-router build_task
2026-01-12 22:03:27 +08:00
YuBaoku ff2eba1f43 [CI] Temporarily disable fp8_cases in base_tests (#5963)
* [CI] Temporarily disable fp8_cases in base_tests
2026-01-08 23:29:37 +08:00
Jiaxin Sui dc170e3005 [XPU][CI]Update CI workflow to include all file types (#5943)
Removed paths-ignore for markdown and text files.
2026-01-08 12:03:26 +08:00
YuBaoku 5088d4acdb [CI] Add daily build_linux jobs for CUDA 12.9 (#5936)
To extend the daily CI coverage by adding Linux build jobs for CUDA 12.9.
2026-01-07 23:20:11 +08:00
YuBaoku 37a128e240 [CI] Fix reusable workflow output mapping in _build_linux_rl.yml
Fix incorrect job reference in reusable workflow outputs, which caused the RL wheel path to be dropped.
2026-01-04 21:22:07 +08:00
YuBaoku 55f77e9ab1 [CI] Add commit-level build_linux task for RL (#5857) 2026-01-04 20:31:27 +08:00
YuBaoku 98519ee2e9 [CI] Fix archive URL injection in tag image build (#5828) 2025-12-30 14:28:17 +08:00
YuBaoku c3ccfa974c [CI] Fix path error and port conflict (#5803) 2025-12-27 12:50:58 +08:00
YuBaoku 8808dd1fed [CI] Enable custom_device_check in CI rerun (#5786)
* [CI] Enable custom_device_check in CI rerun
2025-12-26 14:09:16 +08:00