LoreonLabsPlatform

Overview

Intelligence

Markets
Builders
Research
Narratives
Ecosystems
Launchpads

Discover

Search
Sources

Python

verl

verl: Volcano Engine Reinforcement Learning for LLMs

PythonEmerging

Stars

—

Forks

—

Contributors

8

Last push

1mo ago

Recent commits

Latest commits.

[megatron] fix: ValueError when unpacking preprocess_thd_engine result in router replay (#5891)
b45ee32guillemgt2mo ago
[model] fix: replace inplace += with out-of-place addition in dummy visual forward (#5881)
f92bc5creonokiy2mo ago
[megatron] fix: enable_routing_replay fails with MLATransformerConfig… (#5884)
b90edefVadim Vorobev2mo ago
[cfg] fix: sync strategy from ActorConfig/CriticConfig to EngineConfig (#5885)
74dc16cYifan Wu2mo ago
[ci] fix: fix machine label for nightly_ascend.yml (#5887)
5b3b597yyyy20002mo ago

[4/n][trainer] feat: flowgrpo - add diffusers + fsdp engine support (#5802)

d5c5daaCheung Ka Wai3mo ago

[trainer] fix: handle empty response_mask in calculate_debug_metrics (#5860)

ebb5663Jackie20493mo ago

[megatron] fix: support critic model (#5870)

1625391Joel3mo ago

Top contributors

Builders behind this project.

eric-haibin-lin