LoreonLabsPlatform

Overview

Intelligence

Markets
Builders
Research
Narratives
Ecosystems
Launchpads

Discover

Search
Sources

Other

verl

verl: Volcano Engine Reinforcement Learning for LLMs

OtherEmerging

Stars

—

Forks

—

Contributors

8

Last push

10mo ago

Recent commits

Latest commits.

[BREAKING][rollout] feat: Added asynchronous reward model calculation in agent loop (#3152)
844c929echo-rain10mo ago
[doc] fix: add rStar2-Agent as work using verl (#3298)
ef43469Jiarui Fang（方佳瑞）10mo ago
[perf] feat: add npu silu &expand the scope of patch models (#3260)
abe5e71Chunyu10mo ago
[rollout] feat: Refactor agentloop multiturn (#3171)
f1aeb92Shizhan Lu10mo ago
[fsdp, model] feat: support FSDP model engine (#3270)
91ee0a2Chi Zhang10mo ago

[fsdp] feat: add NPU fusion kernels for Qwen3 MoE (#3221)

c780fc3Shangwei-Li10mo ago

[hardware] fix: update source in dockerfile.rocm (#3284)

fd1a121Ethan (Yusheng) Su10mo ago

[training_utils] fix: allow empty image_key/video_key in rl dataset (#3281)

1422720ℍ𝕠𝕝𝕝𝕠𝕨 𝕄𝕒𝕟10mo ago

Top contributors

Builders behind this project.

eric-haibin-lin