[Bugfix] Miscalculated latency lead to time_to_first_token_seconds inaccurate. (#6686)

2024-07-24 23:58:42 +08:00
parent 2cf0df3381
commit 40468b13fa
2 changed files with 3 additions and 2 deletions
--- a/vllm/spec_decode/spec_decode_worker.py
+++ b/vllm/spec_decode/spec_decode_worker.py
@@ -484,7 +484,7 @@ class SpecDecodeWorker(LoraNotSupportedWorkerBase):
        for both speculation cases (num_lookahead_slots>0) and non-speculation
        cases (e.g. prefill).

-        Returns True iff there are remaining sequences to process.
+        Returns True if there are remaining sequences to process.
        """
        assert self.rank != self._driver_rank