A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 17, 06:45 UTC
docs: add description (#1553)
lots-o committed
Nov 4, 2023 at 01:14 UTC
54ca1ba71deda7eb54f6c9d5002db43039e9edf3
1 file changed
+1
vllm/outputs.py
+1
@@ -53,6 +53,7 @@ class RequestOutput:
53
request_id: The unique ID of the request.
54
prompt: The prompt string of the request.
55
prompt_token_ids: The token IDs of the prompt.
56
+ prompt_logprobs: The log probabilities to return per prompt token.
57
outputs: The output sequences of the request.
58
finished: Whether the whole request is finished.
59
"""