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

Update transformers to v4.55 (#21931)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: isotr0py <2037008807@qq.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
Harry Mellor
2025-08-06 06:56:14 +01:00
committed by GitHub
parent 6e20924350
commit 796bae07c5
13 changed files with 235 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/quantization/test_experts_int8.py
View File

@@ -9,6 +9,8 @@ import pytest
from tests.quantization.utils import is_quant_method_supported
from ..models.registry import HF_EXAMPLE_MODELS
MODELS = ["ai21labs/Jamba-tiny-random", "pfnet/plamo-2-1b"]
@@ -25,6 +27,8 @@ def test_model_experts_int8_startup(
dtype: str,
max_tokens: int,
) -> None:
model_info = HF_EXAMPLE_MODELS.find_hf_info(model)
model_info.check_transformers_version(on_fail="skip")
with vllm_runner(model, dtype=dtype,
quantization="experts_int8") as vllm_model: