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

4
tests/models/language/pooling_mteb_test/test_cross_encoder.py
View File

@@ -12,7 +12,7 @@ RERANK_MODELS = [
RerankModelInfo(
"cross-encoder/ms-marco-TinyBERT-L-2-v2",
architecture="BertForSequenceClassification",
pooling_type="CLS",
seq_pooling_type="CLS",
attn_type="encoder_only",
is_prefix_caching_supported=False,
is_chunked_prefill_supported=False,
@@ -21,7 +21,7 @@ RERANK_MODELS = [
RerankModelInfo(
"tomaarsen/Qwen3-Reranker-0.6B-seq-cls",
architecture="Qwen3ForSequenceClassification",
pooling_type="LAST",
seq_pooling_type="LAST",
attn_type="decoder",
is_prefix_caching_supported=True,
is_chunked_prefill_supported=True,