-
Notifications
You must be signed in to change notification settings - Fork 207
Sync/sync to GitHub v0.1.3 1205 #283
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
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…oken/seq mask & add rollout importance sampling.
…ptimize memory usage during top-k logits computation.
Collaborator
Author
This was referenced Dec 8, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Sync the code with version v0.1.3. The commit messages are as follows:
(fix): update math rule reward worker.
(feat): set RAY_CGRAPH_get_timeout=600.
(fix): vllm 0.11.0 import
(fix): fix train infer ratio/diff mean & add train infer ratio/diff t…
(feat): support vllm beam_search.
(fix): ensure compatibility with transformers version check for causa…
(feat): support pytorch280 docker.
(fix): fix agentic val get_batch state in redundancy env.
(feat): Add support for Qwen-3-next on AMD GPUs.
fix: fix tokenizer usage in llm judge reward worker.
(feat): add vlm option.
(feat): agentic-spec actor worker.
(feat): agentic_filter_task.
(refactor): agentic pipeline modify.
(fix): update error logging for image loading failure.
(fix): fix max_len_mask key.
(feat): add infer_log_probs in agentic.
(feat): update mcore_adapter.
(fix): fix bugs in data fetching for face embeddings.
(feat): add agentic chunk.
(feat): add sglang 0.4.6.post5.
(feat): support offload nccl to save gpu memory.
(feat): support pytorch280 docker.
(fix): fix vllm 0110 model_config.
(refactor): refactor agentic norm.
(feat): add agentic profile metrics.
(feat): sglang 054 patch.
(feat): add enable_reference option.
(fix): fix agentic reference.
(feat): add flash-linear-attention.
(fix): vllm _generate_standard missing prompt_token_ids input args in…
(fix): sglang 054post2 tp worker init wrong.
(fix): vllm add missing argument is_lora in function update_parameter.
(feat): update mcore_adapter.
(fix): fix get_cached_module_file.
(fix): fix bugs with metrics recording in the DPO pipeline.
(feat): add enable_old_logprobs, opt old log probs by cache.
(fix): update image loading logic for byte data in rlvr_vlm_pipeline.py
(feat): mcore_adapter support qwen3vl.
(fix): add force_vit flags for image and video processing in Qwen3 VL…
(feat): add qwen3-vl example.
(feat): mock infer.
(feat): add qwen3-vl 32B example.
(feat): add sequence packing for sft pipeline and distill pipeline, o…
(feat): add alive check.
(feat): sglang support dp-attention.
(fix): set broadcast_non_tensor_batch for old_logprobs.
(fix): fix vllm get_metrics exception.
(fix): fix vllm 0110.
(fix): fix AgenticAcotrWorker import.