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

[Model][6/N] Improve all pooling task | Support chunked prefill with ALL pooling (#27145)

Browse Source 
Signed-off-by: wang.yuqi <noooop@126.com>
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
wang.yuqi
2025-12-04 21:44:15 +08:00
committed by GitHub
parent 1b7c7f5159
commit 74c4d80c6c
15 changed files with 224 additions and 93 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
tests/test_config.py
View File

@@ -629,8 +629,8 @@ def test_s3_url_different_models_create_different_directories(mock_pull_files):
(
"internlm/internlm2-1_8b-reward",
"decoder",
False,
"Pooling models with all pooling does not support chunked prefill.",
True,
"Pooling models with causal attn and all pooling support chunked prefill.",
),
(
"BAAI/bge-base-en",
@@ -748,8 +748,8 @@ def test_is_chunked_prefill_supported(
(
"internlm/internlm2-1_8b-reward",
"decoder",
False,
"Pooling models with all pooling does not support prefix caching.",
True,
"Pooling models with causal attn and all pooling support prefix caching.",
),
(
"BAAI/bge-base-en",