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_nemotron.py
View File

@@ -19,7 +19,7 @@ EMBEDDING_MODELS = [
"nvidia/llama-nemotron-embed-1b-v2",
architecture="LlamaBidirectionalModel",
mteb_score=0.689164662128673,
pooling_type="MEAN",
seq_pooling_type="MEAN",
attn_type="encoder_only",
is_prefix_caching_supported=False,
is_chunked_prefill_supported=False,
@@ -32,7 +32,7 @@ RERANK_MODELS = [
architecture="LlamaBidirectionalForSequenceClassification",
chat_template_name="nemotron-rerank.jinja",
mteb_score=0.33994,
pooling_type="MEAN",
seq_pooling_type="MEAN",
attn_type="encoder_only",
is_prefix_caching_supported=False,
is_chunked_prefill_supported=False,