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

[Model] Support TP/PP/mamba2 kernel for PLaMo2 (#19674)

Browse Source 
Signed-off-by: Shinichi Hemmi <shemmi@preferred.jp>
Signed-off-by: Shinichi Hemmi <50256998+Alnusjaponica@users.noreply.github.com>
Co-authored-by: Calvin Metzger <metzger@preferred.jp>
Co-authored-by: Sixue Wang <cecilwang@preferred.jp>
This commit is contained in:
Shinichi Hemmi
2025-07-28 14:00:47 +09:00
committed by GitHub
parent 15a72ac478
commit c7ffe93d9c
4 changed files with 376 additions and 224 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/quantization/test_experts_int8.py
View File

@@ -9,7 +9,7 @@ import pytest
from tests.quantization.utils import is_quant_method_supported
MODELS = ["ai21labs/Jamba-tiny-random"]
MODELS = ["ai21labs/Jamba-tiny-random", "pfnet/plamo-2-1b"]
@pytest.mark.skipif(not is_quant_method_supported("experts_int8"),