Hugging Face's logo

zhangzhifang
/
verl-agent

Safetensors
Model card Files
xet
 Community
verl-agent / docs

Commit History

Add memory manager & Use config in env_manager (#90)
cfe3636
unverified

Lang Feng commited on

Framework Comparison Chart (#85)
b1956b6
unverified

Lang Feng commited on

Major Update: merge latest verl (#54)
823e1b4
unverified

Lang Feng 湛露先生 AoShen Franz Srambical BaiqingL BearBiscuit HL Blue Space tongyx361 Mantas Bakšys Mert Unsal yangwang92 Patrik Bartak Junrong Lin BearBiscuit05 Leege233 sicer wuxibin shengguangming wangfuchun-fc DuCross Qunhong Zeng Dai, Weinan runluo PPPisOK hiyouga Haibin Lin pengsun000 Hunter Zhang Changlong Xiang Long zyzshishui wangyeyeye zhaochenyang20 jrlin HollowMan6 ztonyzhao icejieke lixiaoguang12 Earl St Sauver Hongpeng Guo Wang Zhang Wang Zhang Jinn yhyang201 QQSong Changlong Yu changlyu chenhaiquan yushengsu Yusheng Su none06630663 ShareLer Xiang Long Rihong Qiu Yuhua Jiang Swtheking openhands Wei Wu commited on

Update README.md (#46)
f2cedd4
unverified

Lang Feng commited on

update scripts and readme
ff1753b

langfeng01 commited on

Merge VeRL
d9b6074

langfeng01 commited on

Merge remote-tracking branch 'upstream/main' into langfeng-merge-verl
b2db55a

langfeng01 commited on

Megatron checkpoint default not save hf_models, and provide model merge tool. (#780)
004f536
unverified

Blue Space commited on

Fix typo on installation guide (#813)
f2a9cd7
unverified

dingyuan commited on

docs: update checkpoint doc (#800)
e067b23
unverified

Blue Space commited on

doc: upgrade to vllm 0.8.2 (#769)
6cfac09
unverified

hiyouga commited on

docs: doc improvements via Openhands, add SimpleRL-Zoo (#764)
26e9abd
unverified

HL commited on

docs: support AMD (Rocm Kernel) - Merge upstream changes and update AMD tutorial (#741)
8e2b545
unverified

yushengsu HL commited on

docs: fix sglang installation rendering (#762)
6bbf521
unverified

HL commited on

recipe: add reproducible PRIME baseline (#753)
ad66e93
unverified

zfwww commited on

[docs] Update the doc for vllm >= 0.8 (#755)
f868e07
unverified

BearBiscuit commited on

first commit
12d92c7

langfeng01 commited on

[feat] Megatron checkpoint support for current Llama and Qwen models (#687)
7fe626c
unverified

Blue Space caaatch22 uygnef sharele commited on

docs: add vllm 0.8 page (#694)
8279a23
unverified

hiyouga commited on

[misc] fix the wrong url (#657)
cd38674
unverified

Yuqian Fu commited on

[rollout] feat: add SGLang as rollout engine to verl (#490)
da627f4
unverified

Junrong Lin zhaochenyang20 commited on

[fix] fix python env issue in install (#619)
6f4ead0
unverified

Fengqing Jiang commited on

[config] feat: lr_warmup_steps (#564)
578b68e
unverified

tongyx361 commited on

[Config] Providing an option to turn off `torch.compile` in actor (#554)
8a74466
unverified

hongpeng-guo commited on

doc: add multinode training and debug tutorial (#585)
1d40286
unverified

wuxibin commited on

docs: fix hardcoded parameters in the Slurm example (#588)
aeb30ab
unverified

Chenhui Zhang commited on

[doc] update megatron core_r0.11.0 documentation (#562)
730ac32
unverified

Blue Space commited on

feat: support loading reward function from an external file (#452)
fb0f2a8
unverified

Lumeng Wu commited on

[misc] feat: make filter long prompt an option (#506)
94a4644
unverified

Guangming Sheng commited on

[Hardware] Support AMD (Rocm kernel) (#360)
79e7412
unverified

Yusheng (Ethan) Su commited on

[docs] update logger documentation (#482)
ec6ac97
unverified

Ze-Yi LIN commited on

support speed up downloading model from modelscope (#463)
b908c6f
unverified

Hong Zhang hiyouga commited on

Update install.rst fix typo (#450)
e3ace58
unverified

celestialli commited on

vllm: fix issue #438 (#440)
0703b8b
unverified

ZSL98 commited on

docs: add hf ckpt to faq, and include verl apis in the website (#427)
3cd0563
unverified

HL commited on

fix: 2 typos (#435)
ba2e6d3
unverified

Lumeng Wu commited on

Update vLLM>=0.7 doc (#432)
2c4b3d1
unverified

ZSL98 commited on

apis: add data proto to documentation page. use copy_to_local instead of copy_local_path_from_hdfs (#358)
28b62eb
unverified

HL commited on

[Fix] Deprecate `val_batch_size` (#353)
81f021f
unverified

tongyx361 commited on

algo: Rloo advantage estimator (#341)
c1f52c2
unverified

zfwww commited on

docs: add faq for vllm illegal memory access (#333)
7ada98d
unverified

HL commited on

docs: add an example for Ray on Slurm (#309)
f47ddaa
unverified

Chenhui Zhang commited on

Fix wrongs args desc . (#294)
90efe31
unverified

湛露先生 commited on

[misc] feat: support offload parameter and optimizer during rollout (#284)
49c2127
unverified

Guangming Sheng commited on

distro: make liger-kernel optional. do not rely on requirement.txt during setup (#286)
cce1ad8
unverified

HL commited on

[doc] Give an additional instruction in building nightly vLLM (#282)
99b5d7c
unverified

ZSL98 zhangshulai commited on

[testing][rollout] feat: support integration of vllm>=0.7.0 (spmd-version) (#209)
787abd3
unverified

ZSL98 zhangshulai commited on

[doc] feat: update remove_padding usage in perf tuning (#264)
8b23fcf
unverified

Guangming Sheng commited on

docs: fix remax algorithm table format (#254)
0486cea
unverified

HL commited on

Fix wrong code path in docs. (#256)
45677de
unverified

湛露先生 commited on