Motivation

Support specifying the content returned by logprobes by adding the startup parameter --logprobs-mode, default is raw_logprobs.

Options: raw_logprobs, processed_logprobs, raw_logits, processed_logits

Raw means the values before applying logit processors, like bad words. Processed means the values after applying such processors.

TODO: Speculative decoding support processed logprob.

Modifications

Usage or Command

python -m fastdeploy.entrypoints.openai.api_server \
    --model "/models/ERNIE-4.5-0.3B-Paddle" \
    --tensor-parallel-size 1 \
    --port 8112 \
    --enable-logprob \
    --logprobs-mode raw_logits

Accuracy Tests

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.