Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / volcengine/verl issues and pull requests
#83 - [misc] feat: add several useful functions in protocol
Pull Request -
State: closed - Opened by PeterSH6 about 1 month ago
- 2 comments
#82 - No module named 'megatron.optimizer'
Issue -
State: closed - Opened by Wraythh about 1 month ago
- 1 comment
#81 - Fix repeat
Pull Request -
State: closed - Opened by caoshiyi about 1 month ago
- 1 comment
#80 - [rollout] feat: support best-of-n generation in vLLM
Pull Request -
State: closed - Opened by PeterSH6 about 1 month ago
#79 - [Pending SGLang] Support torch.compile and allow disabling FSDP
Pull Request -
State: open - Opened by fzyzcjy about 1 month ago
#78 - Validation dataset silently drops last batch
Issue -
State: closed - Opened by fzyzcjy about 1 month ago
- 3 comments
#77 - RayTaskError
Issue -
State: closed - Opened by Raf-Chen about 1 month ago
- 2 comments
Labels: bug, vllm related
#76 - Resume from checkpoints
Issue -
State: open - Opened by fzyzcjy about 1 month ago
- 2 comments
#75 - Tiny refactor and cleanup
Pull Request -
State: open - Opened by fzyzcjy about 1 month ago
- 2 comments
#74 - Support Mlflow, allow forward to have different batch size, compute more metrics
Pull Request -
State: closed - Opened by fzyzcjy about 1 month ago
- 1 comment
#73 - Question about actor training-rollout resharding
Issue -
State: open - Opened by 0oshowero0 about 1 month ago
- 2 comments
#72 - [community] docs: fix WeChat link
Pull Request -
State: closed - Opened by eric-haibin-lin about 1 month ago
#72 - [community] docs: fix WeChat link
Pull Request -
State: closed - Opened by eric-haibin-lin about 1 month ago
#71 - [community] docs: fix WeChat link
Pull Request -
State: closed - Opened by eric-haibin-lin about 1 month ago
#71 - [community] docs: fix WeChat link
Pull Request -
State: closed - Opened by eric-haibin-lin about 1 month ago
#70 - [doc] fix: experiment section url
Pull Request -
State: closed - Opened by PeterSH6 about 1 month ago
#70 - [doc] fix: experiment section url
Pull Request -
State: closed - Opened by PeterSH6 about 1 month ago
#69 - does this framework support long-generation such 8k-16k
Issue -
State: closed - Opened by yyht about 1 month ago
- 3 comments
#69 - does this framework support long-generation such 8k-16k
Issue -
State: open - Opened by yyht about 1 month ago
- 1 comment
#68 - Support RLOO/GRPO/REINFORCE?
Issue -
State: open - Opened by fzyzcjy about 1 month ago
- 24 comments
#68 - Support RLOO/GRPO/REINFORCE?
Issue -
State: open - Opened by fzyzcjy about 1 month ago
- 24 comments
#67 - Super tiny fix typo in title
Pull Request -
State: closed - Opened by fzyzcjy about 1 month ago
- 2 comments
#67 - Super tiny fix typo in title
Pull Request -
State: closed - Opened by fzyzcjy about 1 month ago
- 2 comments
#66 - Missing doc about "Algorithm Baselines"
Issue -
State: closed - Opened by fzyzcjy about 1 month ago
- 6 comments
#65 - [misc] fix: weak reference of WorkerDict in RayTrainer
Pull Request -
State: closed - Opened by PeterSH6 about 1 month ago
#65 - [misc] fix: weak reference of WorkerDict in RayTrainer
Pull Request -
State: closed - Opened by PeterSH6 about 1 month ago
#64 - Actor model didn't update correctly when upgrade megatron to core-r0.6.0
Issue -
State: open - Opened by Wodswos about 2 months ago
- 7 comments
#63 - [install] chore: add pyproject.toml. make vllm default dependency
Pull Request -
State: closed - Opened by eric-haibin-lin about 2 months ago
#62 - package confilct
Issue -
State: closed - Opened by hljjjmssyh about 2 months ago
- 1 comment
#61 - [misc] feat: remove @ray.remote on workers to allow inheritance
Pull Request -
State: closed - Opened by PeterSH6 about 2 months ago
#60 - fix response_mask index
Pull Request -
State: closed - Opened by huiyeruzhou about 2 months ago
- 2 comments
#59 - [install] fix: revert pyproj.toml and fix tensordict req
Pull Request -
State: closed - Opened by eric-haibin-lin about 2 months ago
#58 - FIRE sampling added.
Pull Request -
State: open - Opened by laonahongchen about 2 months ago
#57 - Add pyproject.toml
Pull Request -
State: closed - Opened by pcmoritz about 2 months ago
- 1 comment
#56 - [example] docs: improve the quickstart documentation
Pull Request -
State: closed - Opened by eric-haibin-lin about 2 months ago
#55 - [ppo] chore: remove unused flash_attn dependency, and add docs for GSM8k reward
Pull Request -
State: closed - Opened by eric-haibin-lin about 2 months ago
- 1 comment
#54 - [algorithm] docs: add steps to reproduce PPO algorithm results
Pull Request -
State: closed - Opened by eric-haibin-lin about 2 months ago
#53 - Do we have plans for data packing?
Issue -
State: closed - Opened by YixinSong-e about 2 months ago
- 7 comments
#52 - [BREAKING][refact]: move actor/critic/hybrid_engine/reward_model/rollout/workers out of ppo directory for reuse
Pull Request -
State: closed - Opened by PeterSH6 about 2 months ago
#51 - Question about recomputation in actor module
Issue -
State: closed - Opened by 0oshowero0 about 2 months ago
- 3 comments
#50 - (fix): fix values response mask in dp critic.
Pull Request -
State: closed - Opened by PanAndy about 2 months ago
- 4 comments
#49 - [sft] feat: fix sft dataset with latest preprocess code
Pull Request -
State: closed - Opened by eric-haibin-lin about 2 months ago
#48 - Calling for Improving Robustness of FSDP-vLLM Rollout
Issue -
State: closed - Opened by nwiad about 2 months ago
- 4 comments
#47 - api: rename tracking logger to wandb logger type
Pull Request -
State: closed - Opened by eric-haibin-lin about 2 months ago
#46 - [ray] latest ray compatibility
Issue -
State: closed - Opened by eric-haibin-lin about 2 months ago
- 1 comment
#45 - [BREAKING][core] move single_controller into verl directory
Pull Request -
State: closed - Opened by PeterSH6 about 2 months ago
#44 - [doc] add a new quickstart section
Pull Request -
State: closed - Opened by PeterSH6 about 2 months ago
#43 - [example] add a split placement tutorial
Pull Request -
State: closed - Opened by PeterSH6 about 2 months ago
- 1 comment
#42 - Are optimizer states reloaded or offloaded during the conversion from actor training to actor rollout?
Issue -
State: closed - Opened by G1aZzz 2 months ago
- 1 comment
#41 - [distro] feat: add docker support
Pull Request -
State: closed - Opened by eric-haibin-lin 2 months ago
#40 - Does this framework support full parameter PPO tuning for the Qwen2.5-14B model on 8-A100 GPUs with 80GB memory each?
Issue -
State: open - Opened by hljjjmssyh 2 months ago
- 1 comment
#39 - WIP: Dockerfile
Pull Request -
State: closed - Opened by eric-haibin-lin 2 months ago
#38 - [ci] feat: add more CI workflow
Pull Request -
State: closed - Opened by PeterSH6 2 months ago
- 3 comments
#37 - [distro] refactor: cleanup dependencies in setup script
Pull Request -
State: closed - Opened by eric-haibin-lin 2 months ago
#36 - [tokenizer] feat: support tokenizers whose pad_token_id is none
Pull Request -
State: closed - Opened by eric-haibin-lin 2 months ago
#35 - [docs] feat: add related publications
Pull Request -
State: closed - Opened by eric-haibin-lin 2 months ago
#34 - [model] feat: support models without pad_token
Pull Request -
State: closed - Opened by eric-haibin-lin 2 months ago
- 1 comment
#33 - [rollout] feat: support vLLM v0.6.3 and fix hf rollout import issue
Pull Request -
State: closed - Opened by PeterSH6 2 months ago
#32 - [example] fix: make wandb optional dependency. allow extra args in existing scripts
Pull Request -
State: closed - Opened by eric-haibin-lin 2 months ago
#31 - [example] fix: fix math circular dependency
Pull Request -
State: closed - Opened by eric-haibin-lin 2 months ago
#30 - [misc] fix issue in hf_weight_loader and fix typo in doc
Pull Request -
State: closed - Opened by PeterSH6 2 months ago
#29 - Why create_colocated_worker_cls and spawn
Issue -
State: closed - Opened by eelxpeng 2 months ago
- 3 comments
#28 - [ci] test lint ci and lint tests dir
Pull Request -
State: closed - Opened by PeterSH6 2 months ago
- 1 comment
#27 - [misc] feat: add gemma example for small scale debug and fix gradient checkpoint in critic
Pull Request -
State: closed - Opened by PeterSH6 2 months ago
#26 - enable_gradient_checkpointing is not working
Issue -
State: open - Opened by Vamix 2 months ago
- 2 comments
#25 - Questions Regarding Generation Weights Offloading and Buffer Usage
Issue -
State: closed - Opened by metaqiang 2 months ago
- 1 comment
#24 - Unexpected Increase in Rollout Time After Reducing num_hidden_layers in deepseek-llm-7b-chat Model
Issue -
State: open - Opened by metaqiang 3 months ago
- 2 comments
#23 - [ci] feat: add test files for ray hybrid programming model
Pull Request -
State: closed - Opened by PeterSH6 3 months ago
#22 - [Roadmap] veRL Development Roadmap
Issue -
State: open - Opened by PeterSH6 3 months ago
- 1 comment
#21 - Basic Tutorial: Adding a New LLM Inference/Serving Backend
Issue -
State: open - Opened by PeterSH6 3 months ago
- 1 comment
Labels: enhancement, generation
#20 - Is non-RmPad version model and RmPad verison mdoel interchangeable?
Issue -
State: open - Opened by yanggthomas 3 months ago
- 5 comments
#19 - [chore] remove unnecessary updating of `_worker_names`
Pull Request -
State: closed - Opened by kevin85421 3 months ago
- 7 comments
#18 - [chore] Break the loop after obtaining the register_center actor
Pull Request -
State: closed - Opened by kevin85421 3 months ago
- 1 comment
#17 - Debugging issue with bind_index
Pull Request -
State: closed - Opened by anmscale 3 months ago
#16 - 关于数据和参数切分的性能测试问题
Issue -
State: closed - Opened by metaqiang 3 months ago
- 4 comments
#15 - [RFC] Megatron-LM and MCore maintaining issues for veRL
Issue -
State: open - Opened by PeterSH6 3 months ago
Labels: enhancement, megatron
#14 - Why the `magatron_v4.patch` is needed?
Issue -
State: open - Opened by hxdtest 3 months ago
- 4 comments
#13 - KeyError: 'raw_prompt'
Issue -
State: open - Opened by YixinSong-e 3 months ago
- 2 comments
#12 - Hangs during vllm rollout, no error message
Issue -
State: open - Opened by Vamix 3 months ago
- 5 comments
Labels: bug, vllm related
#11 - 有提供性能调试的手段吗?
Issue -
State: closed - Opened by metaqiang 3 months ago
- 14 comments
#10 - 启动训练脚本出现偶发性ray.exceptions.ActorDiedError错误
Issue -
State: closed - Opened by metaqiang 3 months ago
- 2 comments
#9 - [misc] fix: vllm gpu executor issue when world_size is 1 and typo in doc
Pull Request -
State: closed - Opened by PeterSH6 3 months ago
#8 - Docker image support
Issue -
State: closed - Opened by SolenoidWGT 3 months ago
- 3 comments
#7 - [misc] fix: unknown keyword arg model for single gpu and file name math conflict
Pull Request -
State: closed - Opened by goriri 3 months ago
- 2 comments
#6 - Can I run ppo in llama3.1-70B-instruct?
Issue -
State: open - Opened by cingtiye 3 months ago
- 1 comment
Labels: question
#5 - whether the auto device mapping code in the paper has been uploaded?
Issue -
State: closed - Opened by Zeroreoo 3 months ago
- 2 comments
#4 - [misc] feat: update tutorial for opensource version
Pull Request -
State: closed - Opened by PeterSH6 3 months ago
#3 - [misc] fix: resolve pypi missing directory
Pull Request -
State: closed - Opened by PeterSH6 3 months ago
#2 - [doc] feat: fix typo and delete deprecated config element
Pull Request -
State: closed - Opened by PeterSH6 3 months ago
#1 - [release] feat: first release version on pypi v0.1.1
Pull Request -
State: closed - Opened by PeterSH6 3 months ago