Motivation

Add the switch of using CUDAGraph with Draft Model. CUDAGraph can be used in Draft Model and Target Model respectively.

Modifications

Add the flag draft_model_use_cudagraph.

Usage or Command

draft_model_use_cudagraph defaults to False, close command:

 --graph-optimization-config '{"use_cudagraph":true,  "use_unique_memory_pool":true, "draft_model_use_cudagraph":true}'

Accuracy Tests

Pass

Checklist

• Add at least a tag in the PR title.
  • Tag list: [[FDConfig],[APIServer],[Engine], [Scheduler], [PD Disaggregation], [Executor], [Graph Optimization], [Speculative Decoding], [RL], [Models], [Quantization], [Loader], [OP], [KVCache], [DataProcessor], [BugFix], [Docs], [CI], [Optimization], [Feature], [Benchmark], [Others], [XPU], [HPU], [GCU], [DCU], [Iluvatar], [Metax]]
  • You can add new tags based on the PR content, but the semantics must be clear.
• Format your code, run pre-commit before commit.
• Add unit tests. Please write the reason in this PR if no unit tests.
• Provide accuracy results.
• If the current PR is submitting to the release branch, make sure the PR has been submitted to the develop branch, then cherry-pick it to the release branch with the [Cherry-Pick] PR tag.