biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Refactor] Separate sequence and token pooling types (#32026)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2026-01-10 12:53:24 +08:00
committed by GitHub
parent 52d428295d
commit 583a90e005
42 changed files with 324 additions and 204 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/entrypoints/llm.py
View File

@@ -172,7 +172,7 @@ class LLM:
The available overrides depend on the model that is being run.
For example, for Phi-3-Vision: `{"num_crops": 4}`.
pooler_config: Initialize non-default pooling config for the pooling
model. e.g. `PoolerConfig(pooling_type="mean", normalize=False)`.
model. e.g. `PoolerConfig(seq_pooling_type="MEAN", normalize=False)`.
compilation_config: Either an integer or a dictionary. If it is an
integer, it is used as the mode of compilation optimization. If it
is a dictionary, it can specify the full compilation configuration.