Skip to content

[doc] remove vllm version warning in grpo #4204

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
May 14, 2025
Merged

Conversation

hjh0119
Copy link
Collaborator

@hjh0119 hjh0119 commented May 14, 2025

PR type

  • Bug Fix
  • New Feature
  • Document Updates
  • More Models or Datasets Support

PR information

#4202

Since GRPO already supports vLLM 0.8 in #4097, the warning about the vLLM version in the documentation can be removed.

Experiment results

Paste your experiment result here(if needed).

@hjh0119 hjh0119 merged commit 04b2d28 into modelscope:main May 14, 2025
1 check passed
@hjh0119 hjh0119 deleted the doc-514 branch May 14, 2025 05:39
tastelikefeet added a commit to tastelikefeet/swift that referenced this pull request May 15, 2025
* commit '06d43a8da8005fa16dbb39a5c4c9a29211c7d39b': (24 commits)
  fix qwen2_5_vl VIDEO_TOTAL_PIXELS (modelscope#4236)
  [rlhf] prepare_model for ref_model & reduce peak memory in dpo (modelscope#4232)
  update docs (modelscope#4235)
  fix loss_scale (modelscope#4229)
  fix eval extral args (modelscope#4227)
  fix task type judgement in rlhf (modelscope#4228)
  fix val_dataset_shuffle (modelscope#4226)
  fix get reward model (modelscope#4225)
  fix packing  multi_node (modelscope#4222)
  fix mm packing (modelscope#4217)
  [grpo] set system in inputs (modelscope#4214)
  Refactor packing (modelscope#4207)
  [grpo] fix colocate + tp (modelscope#4209)
  [doc] remove vllm version warning in grpo (modelscope#4204)
  fix ppo reward model (modelscope#4200)
  fix ppo init model (modelscope#4199)
  support yarn rope (modelscope#4197)
  [grpo] code refactor (modelscope#4097)
  update docs (modelscope#4189)
  support deepseek_prover_v2 (modelscope#4184)
  ...

# Conflicts:
#	swift/trainers/rlhf_trainer/rlhf_mixin.py
#	swift/trainers/sequence_parallel/ulysses.py
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants