Regarding router replay or "keep routing", the blog seems say "No current open-source async RL library implements this." Doesn't Megatron support this feature?
Joseph Lee
jiosephlee
AI & ML interests
None yet
Recent Activity
commentedon an article 3 days ago
Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries updated a model 5 days ago
jiosephlee/grpo-tdc-gptoss-dequant-unsloth-3t-v4-ep1-0315_0046 published a model 5 days ago
jiosephlee/grpo-tdc-gptoss-dequant-unsloth-3t-v4-ep1-0315_0046Organizations
None yet
commentedon Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries 3 days ago
updated a
model 5 days ago
published a
model 5 days ago
updated a
model 6 days ago
published a
model 6 days ago
updated a
model 7 days ago
published a
model 7 days ago
updated a
model 8 days ago
published a
model 8 days ago
updated a
model 8 days ago
published a
model 8 days ago
updated a
model 8 days ago
published a
model 8 days ago
updated a
model 8 days ago
published a
model 8 days ago
updated a
model 9 days ago
published a
model 9 days ago
updated a
model 9 days ago
published a
model 9 days ago
published a
model 10 days ago