20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Doc] Fix misleading log during multi-modal profiling (#14955)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung 2025-03-17 21:14:32 +08:00 committed by GitHub
parent 2bb0e1a799
commit 166a168b0f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/multimodal/profiling.py
View File

@ -218,8 +218,10 @@ class MultiModalProfiler(Generic[_I]):
# V0 does not support chunked prefill. # V0 does not support chunked prefill.
if total_len > seq_len and not envs.VLLM_USE_V1: if total_len > seq_len and not envs.VLLM_USE_V1:
# `max_num_batched_tokens` is defined by `SchedulerConfig`
logger.warning( logger.warning(
"The context length (%d) of the model is too short " "The sequence length used for profiling ("
"max_num_batched_tokens / max_num_seqs = %d) is too short "
"to hold the multi-modal embeddings in the worst case " "to hold the multi-modal embeddings in the worst case "
"(%d tokens in total, out of which %s are reserved for " "(%d tokens in total, out of which %s are reserved for "
"multi-modal embeddings). This may cause certain " "multi-modal embeddings). This may cause certain "