Skip to content

Publish-only rollout endpoint #3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
jvmncs wants to merge 21 commits into
base: main
Choose a base branch
from
Draft

Publish-only rollout endpoint #3

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
21 commits
Select commit Hold shift + click to select a range
06aec61
Set RAY_USE_UVLOOP=0 for Ray actors (#2050)
zhuzilin Jun 11, 2026
d4aa9c0
[ci] clean up ci (#2055)
zhuzilin Jun 11, 2026
ee72ab5
Use /v1/loads to re-abort server (#2056)
zhuzilin Jun 11, 2026
7459143
[docs] update miles description and chinese version (#2058)
yueming-yuan Jun 12, 2026
0efcab0
Allow zero-GPU rollout router startup (#2057)
zhuzilin Jun 12, 2026
1b0415a
[docker] expose sglang load inflight details (#2070)
zhuzilin Jun 12, 2026
5d7296a
fix(search-r1): stop generation at </search> and </answer> (#2036)
yichuan-w Jun 13, 2026
fec3da9
[docker] upgrade sglang to v0.5.13 (#2072)
zhuzilin Jun 14, 2026
b7fd1ab
cleanup (#2080)
zhuzilin Jun 15, 2026
4c058f6
sync from internal and cleanup (#2081)
zhuzilin Jun 15, 2026
a1dddef
[algo] Add CISPO advantage estimator (MiniMax-M1) (#2067)
EazyReal Jun 15, 2026
e46ca0a
Overlapping data loading and sglang initialization (#2082)
zhuzilin Jun 15, 2026
96cb409
Add ci badge to readme (#2086)
zhuzilin Jun 16, 2026
23c6b0d
Fix CI badge (#2087)
zhuzilin Jun 16, 2026
6269f20
Add rollout_data_transport nixl (#2088)
zhuzilin Jun 16, 2026
93595d1
Add opaque HTTP rollout endpoint mode
jvmncs Jun 4, 2026
d8526ee
Add version-pinned rollout request policy
jvmncs Jun 4, 2026
4b46fd7
Add publish-only disk delta hooks
jvmncs Jun 4, 2026
76510d7
Pipeline publish-only hook awaits by one sync
jvmncs Jun 11, 2026
1499c3e
[docs] document opaque HTTP rollout endpoint and publish-only delta sync
jvmncs Jun 11, 2026
4ea02f0
Fix HTTP-endpoint rollout: return (servers, init_handles) tuple
jvmncs Jun 17, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
90 changes: 4 additions & 86 deletions .github/workflows/pr-test.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@
# This file is auto-generated from the .j2 file via generate_github_workflows.py. Do not edit manually.
################################################################################


name: PR Test

on:
Expand Down Expand Up @@ -29,89 +30,6 @@ concurrency:

jobs:

e2e-test-short:

if: (github.event_name == 'workflow_dispatch') || (github.event.pull_request && contains(github.event.pull_request.labels.*.name, 'run-ci-short'))


runs-on: self-hosted

strategy:
fail-fast: false
matrix:
info: [{"num_gpus": 4, "test_file": "test_qwen3.5_0.8B_gsm8k_async_short.py"}, {"num_gpus": 4, "test_file": "test_qwen3.5_0.8B_gsm8k_short.py"}, {"num_gpus": 4, "test_file": "test_qwen2.5_0.5B_ppo_critic_only_short.py"}, {"num_gpus": 4, "test_file": "test_qwen2.5_0.5B_fanout_short.py"}, {"num_gpus": 4, "test_file": "test_delta_weight_update.py"}]
defaults:
run:
working-directory: ${{ github.workspace }}
env:
GITHUB_COMMIT_NAME: ${{ github.sha }}_${{ github.event.pull_request.number || 'non-pr' }}
WANDB_API_KEY: ${{ secrets.WANDB_API_KEY }}
SLIME_TEST_ENABLE_INFINITE_RUN: ${{ (github.event_name == 'workflow_dispatch' && github.event.inputs.infinite_run) || 'false' }}
SLIME_TEST_USE_DEEPEP: ${{ matrix.info.use_deepep || '0' }}
SLIME_TEST_USE_FP8_ROLLOUT: ${{ matrix.info.use_fp8_rollout || '0' }}
SLIME_TEST_ENABLE_EVAL: ${{ matrix.info.enable_eval || '1' }}

steps:
- name: Checkout repository
uses: actions/checkout@v4



- name: Execute
shell: bash
run: |

docker run --pull=always --rm \
--privileged \
--cap-add SYS_NICE \
--security-opt seccomp=unconfined \
--network host \
--gpus all \
--ipc=host \
--shm-size=16g \
--ulimit memlock=-1 \
--ulimit stack=67108864 \
--memory=0 \
--memory-swap=0 \
-e http_proxy \
-e https_proxy \
-e HTTP_PROXY \
-e HTTPS_PROXY \
-e GITHUB_COMMIT_NAME \
-e WANDB_API_KEY \
-e SLIME_TEST_ENABLE_INFINITE_RUN \
-e SLIME_TEST_USE_DEEPEP \
-e SLIME_TEST_USE_FP8_ROLLOUT \
-e SLIME_TEST_ENABLE_EVAL \
-e TEST_FILE="${{ matrix.info.test_file }}" \
-e TEST_ARGS="${{ matrix.info.test_args || '' }}" \
-e NUM_GPUS="${{ matrix.info.num_gpus }}" \
-v "$GITHUB_WORKSPACE:$GITHUB_WORKSPACE" \
-v /mnt/nvme0n1/slime_ci:/data/slime_ci \
-v /mnt/nvme0n1/slime_ci/models:/root/models \
-v /mnt/nvme0n1/slime_ci/datasets:/root/datasets \
-w "$GITHUB_WORKSPACE" \
slimerl/slime:latest \
bash -lc '
set -euo pipefail
pip install -e . --no-deps --break-system-packages
TEST_PATH="$TEST_FILE"
if [[ "$TEST_PATH" != tests/* ]]; then
TEST_PATH="tests/$TEST_PATH"
fi
if [[ -n "$TEST_ARGS" ]]; then
read -r -a TEST_ARGS_ARRAY < <(printf "%s\n" "$TEST_ARGS")
else
TEST_ARGS_ARRAY=()
fi
if [ "$NUM_GPUS" = "0" ]; then
python "$TEST_PATH" "${TEST_ARGS_ARRAY[@]}"
else
python tests/ci/gpu_lock_exec.py --count "$NUM_GPUS" -- python "$TEST_PATH" "${TEST_ARGS_ARRAY[@]}"
fi
'


e2e-test-sglang-config:

if: (github.event_name == 'workflow_dispatch') || (github.event.pull_request && contains(github.event.pull_request.labels.*.name, 'run-ci-sglang-config'))
Expand Down Expand Up @@ -205,7 +123,7 @@ jobs:
strategy:
fail-fast: false
matrix:
info: [{"num_gpus": 4, "test_file": "test_full_disk_weight_update.py"}, {"enable_eval": "0", "num_gpus": 8, "test_file": "test_quick_start_glm4_9B.py"}, {"num_gpus": 8, "test_file": "test_glm4.7_30B_A3B_pd_mooncake.py"}, {"enable_eval": "0", "num_gpus": 8, "test_file": "test_qwen3_30B_A3B.py", "use_deepep": "1", "use_fp8_rollout": "1"}, {"num_gpus": 8, "test_file": "test_qwen3.6_35B_A3B_pd_mooncake.py", "use_deepep": "1"}, {"enable_eval": "0", "num_gpus": 8, "test_file": "test_qwen3_30B_A3B_r3.py", "use_deepep": "1", "use_fp8_rollout": "1"}, {"enable_eval": "0", "num_gpus": 8, "test_file": "test_qwen3_4B_ppo.py"}, {"enable_eval": "0", "num_gpus": 8, "test_file": "test_qwen3_4B_ppo_disaggregate.py"}, {"enable_eval": "0", "num_gpus": 8, "test_file": "test_qwen3_4B_ppo_train_critic_only.py"}, {"enable_eval": "0", "num_gpus": 8, "test_file": "test_moonlight_16B_A3B.py"}, {"enable_eval": "0", "num_gpus": 8, "test_file": "test_moonlight_16B_A3B_r3.py"}, {"num_gpus": 8, "test_file": "test_mimo_7B_mtp_only_grad.py"}, {"num_gpus": 8, "test_file": "test_qwen3_0.6B_parallel_check.py"}, {"num_gpus": 8, "test_file": "test_qwen2.5_0.5B_debug_rollout_then_train.py"}, {"num_gpus": 8, "test_file": "test_qwen2.5_0.5B_opd_sglang.py"}, {"num_gpus": 6, "test_file": "test_qwen3_4B_external_pd.py"}, {"num_gpus": 4, "test_file": "test_qwen2.5_0.5B_fully_async_short.py"}, {"num_gpus": 8, "test_file": "test_qwen3_4B_streaming_partial_rollout.py"}, {"num_gpus": 4, "test_file": "test_qwen3.5_0.8B_gsm8k_short.py"}, {"num_gpus": 4, "test_file": "test_qwen3.5_0.8B_gsm8k_async_short.py"}, {"num_gpus": 8, "test_args": "--save-optimizer gpu --load-optimizer gpu", "test_file": "test_qwen3_4B_ckpt.py"}, {"num_gpus": 8, "test_args": "--save-optimizer gpu --load-optimizer cpu", "test_file": "test_qwen3_4B_ckpt.py"}, {"num_gpus": 8, "test_args": "--save-optimizer cpu --load-optimizer cpu", "test_file": "test_qwen3_4B_ckpt.py"}, {"num_gpus": 8, "test_args": "--save-optimizer cpu --load-optimizer gpu", "test_file": "test_qwen3_4B_ckpt.py"}, {"num_gpus": 8, "test_args": "--async-save", "test_file": "test_qwen3_4B_ckpt.py"}]
info: [{"num_gpus": 4, "test_file": "test_full_disk_weight_update.py"}, {"enable_eval": "0", "num_gpus": 8, "test_file": "test_quick_start_glm4_9B.py"}, {"num_gpus": 8, "test_file": "test_glm4.7_30B_A3B_pd_mooncake.py"}, {"enable_eval": "0", "num_gpus": 8, "test_file": "test_qwen3_30B_A3B.py", "use_deepep": "1", "use_fp8_rollout": "1"}, {"num_gpus": 8, "test_file": "test_qwen3.6_35B_A3B_pd_mooncake.py", "use_deepep": "1"}, {"enable_eval": "0", "num_gpus": 8, "test_file": "test_qwen3_30B_A3B_r3.py", "use_deepep": "1", "use_fp8_rollout": "1"}, {"enable_eval": "0", "num_gpus": 8, "test_file": "test_qwen3_4B_ppo.py"}, {"enable_eval": "0", "num_gpus": 8, "test_file": "test_qwen3_4B_ppo_disaggregate.py"}, {"enable_eval": "0", "num_gpus": 8, "test_file": "test_qwen3_4B_ppo_train_critic_only.py"}, {"enable_eval": "0", "num_gpus": 8, "test_file": "test_moonlight_16B_A3B.py"}, {"enable_eval": "0", "num_gpus": 8, "test_file": "test_moonlight_16B_A3B_r3.py"}, {"num_gpus": 8, "test_file": "test_mimo_7B_mtp_only_grad.py"}, {"num_gpus": 8, "test_file": "test_qwen3_0.6B_parallel_check.py"}, {"num_gpus": 8, "test_file": "test_qwen2.5_0.5B_debug_rollout_then_train.py"}, {"num_gpus": 8, "test_file": "test_qwen2.5_0.5B_opd_sglang.py"}, {"num_gpus": 6, "test_file": "test_qwen3_4B_external_pd.py"}, {"num_gpus": 4, "test_file": "test_qwen2.5_0.5B_fully_async_short.py"}, {"num_gpus": 4, "test_file": "test_qwen2.5_0.5B_fanout_short.py"}, {"num_gpus": 8, "test_file": "test_qwen3_4B_streaming_partial_rollout.py"}, {"num_gpus": 4, "test_file": "test_qwen3.5_0.8B_gsm8k_short.py"}, {"num_gpus": 4, "test_file": "test_qwen3.5_0.8B_gsm8k_async_short.py"}, {"num_gpus": 8, "test_args": "--save-optimizer gpu --load-optimizer gpu", "test_file": "test_qwen3_4B_ckpt.py"}, {"num_gpus": 8, "test_args": "--save-optimizer gpu --load-optimizer cpu", "test_file": "test_qwen3_4B_ckpt.py"}, {"num_gpus": 8, "test_args": "--save-optimizer cpu --load-optimizer cpu", "test_file": "test_qwen3_4B_ckpt.py"}, {"num_gpus": 8, "test_args": "--save-optimizer cpu --load-optimizer gpu", "test_file": "test_qwen3_4B_ckpt.py"}, {"num_gpus": 8, "test_args": "--async-save", "test_file": "test_qwen3_4B_ckpt.py"}]
defaults:
run:
working-directory: ${{ github.workspace }}
Expand Down Expand Up @@ -454,7 +372,7 @@ jobs:
strategy:
fail-fast: false
matrix:
info: [{"num_gpus": 0, "test_file": "test_megatron_argument_validation.py"}, {"num_gpus": 0, "test_file": "test_dp_schedule.py"}, {"num_gpus": 0, "test_file": "test_cp_utils.py"}, {"num_gpus": 0, "test_file": "test_metric_report.py"}, {"num_gpus": 0, "test_file": "test_metric_report_dist.py"}, {"num_gpus": 0, "test_file": "test_loss_cp_invariance.py"}, {"num_gpus": 0, "test_file": "test_value_temperature.py"}, {"num_gpus": 0, "test_file": "test_rm_f1.py"}, {"num_gpus": 0, "test_file": "test_rm_gpqa.py"}, {"num_gpus": 0, "test_file": "test_rm_math.py"}, {"num_gpus": 0, "test_file": "test_rm_math_dapo.py"}, {"num_gpus": 0, "test_file": "test_rm_deepscaler.py"}, {"num_gpus": 0, "test_file": "test_sample.py"}, {"num_gpus": 0, "test_file": "test_agent_trajectory.py"}, {"num_gpus": 0, "test_file": "test_rollout_validation.py"}, {"num_gpus": 0, "test_file": "test_placement_group.py"}, {"num_gpus": 0, "test_file": "test_external_sglang_engines.py"}, {"num_gpus": 0, "test_file": "utils/test_hf_checkpoint_saver.py"}, {"num_gpus": 0, "test_file": "plugin_contracts/test_plugin_rollout_contracts.py"}, {"num_gpus": 0, "test_file": "plugin_contracts/test_plugin_runtime_hook_contracts.py"}, {"num_gpus": 0, "test_file": "plugin_contracts/test_plugin_path_loading_contracts.py"}, {"num_gpus": 0, "test_file": "plugin_contracts/test_plugin_generate_contracts.py"}]
info: [{"num_gpus": 0, "test_file": "test_megatron_argument_validation.py"}, {"num_gpus": 0, "test_file": "test_dp_schedule.py"}, {"num_gpus": 0, "test_file": "test_cp_utils.py"}, {"num_gpus": 0, "test_file": "test_metric_report.py"}, {"num_gpus": 0, "test_file": "test_metric_report_dist.py"}, {"num_gpus": 0, "test_file": "test_loss_cp_invariance.py"}, {"num_gpus": 0, "test_file": "test_value_temperature.py"}, {"num_gpus": 0, "test_file": "test_cispo_loss.py"}, {"num_gpus": 0, "test_file": "test_rm_f1.py"}, {"num_gpus": 0, "test_file": "test_rm_gpqa.py"}, {"num_gpus": 0, "test_file": "test_rm_math.py"}, {"num_gpus": 0, "test_file": "test_rm_math_dapo.py"}, {"num_gpus": 0, "test_file": "test_rm_deepscaler.py"}, {"num_gpus": 0, "test_file": "test_sample.py"}, {"num_gpus": 0, "test_file": "test_agent_trajectory.py"}, {"num_gpus": 0, "test_file": "test_rollout_validation.py"}, {"num_gpus": 0, "test_file": "test_placement_group.py"}, {"num_gpus": 0, "test_file": "test_external_sglang_engines.py"}, {"num_gpus": 0, "test_file": "utils/test_hf_checkpoint_saver.py"}, {"num_gpus": 0, "test_file": "plugin_contracts/test_plugin_rollout_contracts.py"}, {"num_gpus": 0, "test_file": "plugin_contracts/test_plugin_runtime_hook_contracts.py"}, {"num_gpus": 0, "test_file": "plugin_contracts/test_plugin_path_loading_contracts.py"}, {"num_gpus": 0, "test_file": "plugin_contracts/test_plugin_generate_contracts.py"}]
defaults:
run:
working-directory: ${{ github.workspace }}
Expand Down Expand Up @@ -588,7 +506,7 @@ jobs:
strategy:
fail-fast: false
matrix:
info: [{"num_gpus": 4, "test_file": "test_qwen3.5_0.8B_gsm8k_async_short.py"}, {"num_gpus": 4, "test_file": "test_qwen3.5_0.8B_gsm8k_short.py"}, {"enable_eval": "0", "num_gpus": 8, "test_file": "test_quick_start_glm4_9B.py"}, {"num_gpus": 8, "test_file": "test_glm4.7_30B_A3B_pd_mooncake.py"}, {"enable_eval": "0", "num_gpus": 8, "test_file": "test_qwen3_30B_A3B.py"}, {"num_gpus": 8, "test_file": "test_qwen3.6_35B_A3B_pd_mooncake.py", "use_deepep": "1"}, {"enable_eval": "0", "num_gpus": 8, "test_file": "test_qwen3_4B_ppo.py"}, {"enable_eval": "0", "num_gpus": 8, "test_file": "test_moonlight_16B_A3B.py"}, {"num_gpus": 8, "test_file": "test_mimo_7B_mtp_only_grad.py"}, {"num_gpus": 8, "test_file": "test_qwen3_0.6B_parallel_check.py"}, {"num_gpus": 8, "test_args": "--save-optimizer gpu --load-optimizer gpu", "test_file": "test_qwen3_4B_ckpt.py"}, {"num_gpus": 8, "test_args": "--save-optimizer gpu --load-optimizer cpu", "test_file": "test_qwen3_4B_ckpt.py"}, {"num_gpus": 8, "test_args": "--save-optimizer cpu --load-optimizer cpu", "test_file": "test_qwen3_4B_ckpt.py"}, {"num_gpus": 8, "test_args": "--save-optimizer cpu --load-optimizer gpu", "test_file": "test_qwen3_4B_ckpt.py"}, {"num_gpus": 8, "test_args": "--async-save", "test_file": "test_qwen3_4B_ckpt.py"}, {"num_gpus": 8, "test_file": "test_qwen2.5_0.5B_debug_rollout_then_train.py"}, {"num_gpus": 8, "test_file": "test_qwen2.5_0.5B_opd_sglang.py"}]
info: [{"num_gpus": 4, "test_file": "test_full_disk_weight_update.py"}, {"enable_eval": "0", "num_gpus": 8, "test_file": "test_quick_start_glm4_9B.py"}, {"num_gpus": 8, "test_file": "test_glm4.7_30B_A3B_pd_mooncake.py"}, {"enable_eval": "0", "num_gpus": 8, "test_file": "test_qwen3_30B_A3B.py", "use_deepep": "1", "use_fp8_rollout": "1"}, {"num_gpus": 8, "test_file": "test_qwen3.6_35B_A3B_pd_mooncake.py", "use_deepep": "1"}, {"enable_eval": "0", "num_gpus": 8, "test_file": "test_qwen3_30B_A3B_r3.py", "use_deepep": "1", "use_fp8_rollout": "1"}, {"enable_eval": "0", "num_gpus": 8, "test_file": "test_qwen3_4B_ppo.py"}, {"enable_eval": "0", "num_gpus": 8, "test_file": "test_qwen3_4B_ppo_disaggregate.py"}, {"enable_eval": "0", "num_gpus": 8, "test_file": "test_qwen3_4B_ppo_train_critic_only.py"}, {"enable_eval": "0", "num_gpus": 8, "test_file": "test_moonlight_16B_A3B.py"}, {"enable_eval": "0", "num_gpus": 8, "test_file": "test_moonlight_16B_A3B_r3.py"}, {"num_gpus": 8, "test_file": "test_mimo_7B_mtp_only_grad.py"}, {"num_gpus": 8, "test_file": "test_qwen3_0.6B_parallel_check.py"}, {"num_gpus": 8, "test_file": "test_qwen2.5_0.5B_debug_rollout_then_train.py"}, {"num_gpus": 8, "test_file": "test_qwen2.5_0.5B_opd_sglang.py"}, {"num_gpus": 6, "test_file": "test_qwen3_4B_external_pd.py"}, {"num_gpus": 4, "test_file": "test_qwen2.5_0.5B_fully_async_short.py"}, {"num_gpus": 4, "test_file": "test_qwen2.5_0.5B_fanout_short.py"}, {"num_gpus": 8, "test_file": "test_qwen3_4B_streaming_partial_rollout.py"}, {"num_gpus": 4, "test_file": "test_qwen3.5_0.8B_gsm8k_short.py"}, {"num_gpus": 4, "test_file": "test_qwen3.5_0.8B_gsm8k_async_short.py"}, {"num_gpus": 8, "test_args": "--save-optimizer gpu --load-optimizer gpu", "test_file": "test_qwen3_4B_ckpt.py"}, {"num_gpus": 8, "test_args": "--save-optimizer gpu --load-optimizer cpu", "test_file": "test_qwen3_4B_ckpt.py"}, {"num_gpus": 8, "test_args": "--save-optimizer cpu --load-optimizer cpu", "test_file": "test_qwen3_4B_ckpt.py"}, {"num_gpus": 8, "test_args": "--save-optimizer cpu --load-optimizer gpu", "test_file": "test_qwen3_4B_ckpt.py"}, {"num_gpus": 8, "test_args": "--async-save", "test_file": "test_qwen3_4B_ckpt.py"}]
defaults:
run:
working-directory: ${{ github.workspace }}
Expand Down
Loading
Loading