xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-13 12:46:07 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix doc (#622)

Browse Source
This commit is contained in:
Chaofan Lin 2023-08-01 04:11:57 +08:00 committed by GitHub
parent 953f28cf9a
commit aa39e42c5a
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/config.py
View File

@ -224,7 +224,7 @@ class SchedulerConfig:
a single iteration. a single iteration.
max_num_seqs: Maximum number of sequences to be processed in a single max_num_seqs: Maximum number of sequences to be processed in a single
iteration. iteration.
max_seq_len: Maximum length of a sequence (including prompt max_model_len: Maximum length of a sequence (including prompt
and generated text). and generated text).
""" """

2
vllm/engine/llm_engine.py
View File

@ -353,7 +353,7 @@ class LLMEngine:
if stopped: if stopped:
continue continue
# Check if the sequence has reached max_seq_len. # Check if the sequence has reached max_model_len.
if seq.get_len() > self.scheduler_config.max_model_len: if seq.get_len() > self.scheduler_config.max_model_len:
self.scheduler.free_seq( self.scheduler.free_seq(
seq, SequenceStatus.FINISHED_LENGTH_CAPPED) seq, SequenceStatus.FINISHED_LENGTH_CAPPED)