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

[Frontend][3/n] Make pooling entrypoints request schema consensus | EmbedRequest & ClassifyRequest (#32905)

Browse Source 
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
wang.yuqi
2026-01-23 20:03:44 +08:00
committed by GitHub
parent 3f3f89529d
commit 05f3d714db
11 changed files with 330 additions and 265 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
vllm/pooling_params.py
View File

@@ -38,17 +38,17 @@ class PoolingParams(
# --8<-- [end:common-pooling-params]
## for embeddings models
# --8<-- [start:embedding-pooling-params]
# --8<-- [start:embed-pooling-params]
dimensions: int | None = None
normalize: bool | None = None
# --8<-- [end:embedding-pooling-params]
# --8<-- [end:embed-pooling-params]
## for classification, scoring and rerank
# --8<-- [start:classification-pooling-params]
# --8<-- [start:classify-pooling-params]
softmax: bool | None = None
activation: bool | None = None
use_activation: bool | None = None
# --8<-- [end:classification-pooling-params]
# --8<-- [end:classify-pooling-params]
## for step pooling models
step_tag_id: int | None = None