[W8A8 Block Linear Refactor][2/N] Remove W8A8Fp8BlockLinearOp and adopt Fp8 block linear kernel selections. (#33892)

Signed-off-by: maral <maralbahari.98@gmail.com>
Signed-off-by: Maral <maralbahari.98@gmail.com>
This commit is contained in:
Maral
2026-04-09 08:50:39 +08:00
committed by GitHub
parent 8332078cfd
commit 2e9034c998
35 changed files with 1710 additions and 904 deletions

View File

@@ -246,8 +246,9 @@ def default_vllm_config():
"""
from vllm.config import VllmConfig, set_current_vllm_config
with set_current_vllm_config(VllmConfig()):
yield
config = VllmConfig()
with set_current_vllm_config(config):
yield config
@pytest.fixture()