Skip to content

Actions: NVIDIA-NeMo/RL

Actions

CICD NeMo RL

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
cicd-main.yml
8,270 workflow runs
8,270 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

feat: RL support for custom moe models in dtensor v2 CICD NeMo RL #8600: Pull request #1695 labeled by hemildesai
Queued hemil/automodel-rl
hemil/automodel-rl
Queued
cp: fix: log metrics that can be coerced to scalars (1723) into r0.5.0 CICD NeMo RL #8599: Pull request #1730 labeled by chtruong814
2m 41s cherry-pick-1723-r0.5.0
cherry-pick-1723-r0.5.0
2m 41s
cp: fix: log metrics that can be coerced to scalars (1723) into r0.5.0 CICD NeMo RL #8598: Pull request #1730 labeled by chtruong814
2m 46s cherry-pick-1723-r0.5.0
cherry-pick-1723-r0.5.0
2m 46s
cp: fix: log metrics that can be coerced to scalars (1723) into r0.5.0 CICD NeMo RL #8597: Pull request #1730 opened by chtruong814
2m 42s cherry-pick-1723-r0.5.0
cherry-pick-1723-r0.5.0
2m 42s
feat: RL support for custom moe models in dtensor v2 CICD NeMo RL #8596: Pull request #1695 synchronize by hemildesai
2m 38s hemil/automodel-rl
hemil/automodel-rl
2m 38s
fix: use median instead of mean for logprob error for stability in nightlies CICD NeMo RL #8595: Pull request #1722 labeled by terrykong
In progress test-fix-5
test-fix-5
In progress
fix: use median instead of mean for logprob error for stability in nightlies CICD NeMo RL #8594: Pull request #1722 synchronize by terrykong
2m 35s test-fix-5
test-fix-5
2m 35s
fix: mcore generation config restored in nightly test CICD NeMo RL #8593: Pull request #1720 synchronize by terrykong
2m 53s test-fixes-1
test-fixes-1
2m 53s
fix: mcore generation config restored in nightly test CICD NeMo RL #8592: Pull request #1720 synchronize by terrykong
28s test-fixes-1
test-fixes-1
28s
perf: Add DeepEP support to Megatron Policy CICD NeMo RL #8591: Pull request #1645 labeled by guyueh1
51m 12s parthmannan:pmannan/deepep_mcore_training
parthmannan:pmannan/deepep_mcore_training
51m 12s
feat: Add SGLang rollout backend and tests CICD NeMo RL #8590: Pull request #1674 labeled by guyueh1
Queued RolaoDenthu:add-tests
RolaoDenthu:add-tests
Queued
feat: Add SGLang rollout backend and tests CICD NeMo RL #8589: Pull request #1674 synchronize by RolaoDenthu
2m 43s RolaoDenthu:add-tests
RolaoDenthu:add-tests
2m 43s
feat: Add SGLang rollout backend and tests CICD NeMo RL #8588: Pull request #1674 synchronize by RolaoDenthu
3m 52s RolaoDenthu:add-tests
RolaoDenthu:add-tests
3m 52s
feat: Add SGLang rollout backend and tests CICD NeMo RL #8587: Pull request #1674 synchronize by RolaoDenthu
Action required RolaoDenthu:add-tests
RolaoDenthu:add-tests
Action required
feat: RL support for custom moe models in dtensor v2 CICD NeMo RL #8586: Pull request #1695 labeled by hemildesai
9h 57m 50s hemil/automodel-rl
hemil/automodel-rl
9h 57m 50s
feat: RL support for custom moe models in dtensor v2 CICD NeMo RL #8585: Pull request #1695 synchronize by hemildesai
2m 40s hemil/automodel-rl
hemil/automodel-rl
2m 40s
fix: patch transformer qwen2 forward CICD NeMo RL #8584: Pull request #1728 opened by RayenTian
5m 48s ruit/slice_issue
ruit/slice_issue
5m 48s
fix: gemma3 27b must now have skip_tokenizer_init=False in vllm CICD NeMo RL #8583: Pull request #1721 labeled by yuki-97
Queued test-fix-2
test-fix-2
Queued
cp: fix: Disable cudnn sdpa backend when using activation checkpointing (1717) into r0.5.0 CICD NeMo RL #8582: Pull request #1727 labeled by yuki-97
10h 13m 32s cherry-pick-1717-r0.5.0
cherry-pick-1717-r0.5.0
10h 13m 32s
fix: log metrics that can be coerced to scalars CICD NeMo RL #8581: Pull request #1723 labeled by yuki-97
11h 42m 7s test-fixes-6
test-fixes-6
11h 42m 7s
fix: use median instead of mean for logprob error for stability in nightlies CICD NeMo RL #8580: Pull request #1722 labeled by yuki-97
9h 28m 37s test-fix-5
test-fix-5
9h 28m 37s
fix: mcore generation config restored in nightly test CICD NeMo RL #8579: Pull request #1720 labeled by yuki-97
5h 10m 57s test-fixes-1
test-fixes-1
5h 10m 57s
cp: fix: Disable cudnn sdpa backend when using activation checkpointing (1717) into r0.5.0 CICD NeMo RL #8578: Pull request #1727 labeled by chtruong814
2m 57s cherry-pick-1717-r0.5.0
cherry-pick-1717-r0.5.0
2m 57s
cp: fix: Disable cudnn sdpa backend when using activation checkpointing (1717) into r0.5.0 CICD NeMo RL #8577: Pull request #1727 labeled by chtruong814
2m 53s cherry-pick-1717-r0.5.0
cherry-pick-1717-r0.5.0
2m 53s
cp: fix: Disable cudnn sdpa backend when using activation checkpointing (1717) into r0.5.0 CICD NeMo RL #8576: Pull request #1727 opened by chtruong814
2m 49s cherry-pick-1717-r0.5.0
cherry-pick-1717-r0.5.0
2m 49s