Skip to content

GitLab

Unverified Commit aa39e42c authored by Chaofan Lin's avatar Chaofan Lin Committed by GitHub
Browse files

fix doc (#622)

parent 953f28cf
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 2 deletions
vllm/config.py
View file @ aa39e42c
...@@ -224,7 +224,7 @@ class SchedulerConfig: ...@@ -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).
""" """
......
vllm/engine/llm_engine.py
View file @ aa39e42c
...@@ -353,7 +353,7 @@ class LLMEngine: ...@@ -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)
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment