Sync/sync to GitHub v0.1.3 1205

[PanAndy]

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.

[CLAassistant]

All committers have signed the CLA.

[PanAndy]

#284