Skip to content

Actions: NVIDIA-NeMo/RL

Actions

Community Bot

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
community-bot.yml
2,991 workflow runs
2,991 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

docs: Refactor Home Page and New About Section Community Bot #991: Issue comment #1338 (comment) created by lbliii
15s
15s
fix: Make the optimizer offloading optional Community Bot #990: Issue comment #1404 (comment) created by youngeunkwon0405
17s
17s
fix: Make the optimizer offloading optional Community Bot #989: Issue comment #1404 (comment) created by yuki-97
14s
14s
fix: Use custom chat template also in VLM's Community Bot #988: Issue comment #1344 (comment) created by jseppanen
13s
13s
fix: Make the optimizer offloading optional Community Bot #987: Issue comment #1404 (comment) edited by youngeunkwon0405
14s
14s
fix: Make the optimizer offloading optional Community Bot #986: Issue comment #1404 (comment) created by youngeunkwon0405
13s
13s
fix: Adding mean total tokens per sample to the output log Community Bot #985: Issue comment #1406 (comment) created by youngeunkwon0405
12s
12s
feat: async performance recipe (under test) Community Bot #984: Issue comment #1414 (comment) created by youngeunkwon0405
15s
15s
Qwen3-30B-A3B: Checkpoint Save Failures on Large-Scale GPU Configurations (H100) and Small-Scale GB200 Systems Community Bot #983: Issue comment #1283 (comment) edited by ZhiyuLi-Nvidia
17s
17s
Qwen3-30B-A3B: Checkpoint Save Failures on Large-Scale GPU Configurations (H100) and Small-Scale GB200 Systems Community Bot #982: Issue comment #1283 (comment) created by ZhiyuLi-Nvidia
10s
10s
Support GPT-OSS Model Trainings with Long Context Community Bot #981: Issue comment #1153 (comment) created by ashors1
14s
14s
Support GPT-OSS Model Trainings with Long Context Community Bot #980: Issue #1153 closed by ashors1
15s
15s
Megatron-Bridge submodule version incompatible with GPT-OSS Community Bot #979: Issue comment #1146 (comment) created by ashors1
12s
12s
gpt-oss Mcore support Community Bot #978: Issue comment #869 (comment) created by ashors1
14s
14s
feat: Printing worker id to node.bundle_idx mapping Community Bot #977: Issue comment #1366 (comment) created by youngeunkwon0405
17s
17s
report rl and optimization step differently Community Bot #976: Issue #1435 opened by gshennvm
13s
13s
generalize metric reporting Community Bot #975: Issue #1434 opened by gshennvm
10s
10s
Community Bot Community Bot #974: deleted by ffrujeri
13s
13s
chore: major version bump (torch 2.8, vllm 0.11, ray 2.49) & SP fixes Community Bot #973: Issue comment #1334 (comment) created by youngeunkwon0405
13s
13s
Update and Merge RL IA Refactor Community Bot #972: Issue #1433 opened by lbliii
11s
11s
Support Qwen-3 next in MCore path Community Bot #971: Issue #1431 opened by ahmadki
10s
10s
Support Qwen-3 next in DTensor path Community Bot #970: Issue #1430 opened by ahmadki
13s
13s
fix: Fix megatron checkpoint loading during sft Community Bot #969: Issue comment #836 (comment) created by yfw
14s
14s
cp: fix: Reinitialize model parallel after import (1317) into r0.4.0 Community Bot #968: Issue comment #1428 (comment) created by terrykong
9s
9s
cp: fix: Reinitialize model parallel after import (1317) into r0.4.0 Community Bot #967: Issue comment #1428 (comment) created by zpqiu
16s
16s
ProTip! You can narrow down the results and go further in time using created:<2025-10-27 or the other filters available.