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

[Frontend][torch.compile] CompilationConfig Overhaul (#20283): name change compilation level to compilation mode, deprecation compilation level (#26355)

Browse Source 
Signed-off-by: morrison-turnansky <mturnans@redhat.com>
Signed-off-by: Morrison Turnansky <mturnans@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
This commit is contained in:
Morrison Turnansky
2025-10-14 22:51:16 -04:00
committed by GitHub
parent e66d787bce
commit 96b9aa5aa0
42 changed files with 270 additions and 248 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/model_executor/layers/quantization/utils/w8a8_utils.py
View File

@@ -8,7 +8,7 @@ from packaging import version
from vllm import _custom_ops as ops
from vllm import envs
from vllm.config import CompilationLevel, get_current_vllm_config
from vllm.config import CompilationMode, get_current_vllm_config
from vllm.model_executor.layers.quantization.input_quant_fp8 import QuantFP8
from vllm.model_executor.layers.quantization.utils.quant_utils import GroupShape
from vllm.platforms import current_platform
@@ -419,7 +419,7 @@ class Fp8LinearOp:
if pad_output is None:
config = get_current_vllm_config().compilation_config
pad_output = (
config.level < CompilationLevel.PIECEWISE
config.mode < CompilationMode.VLLM_COMPILE
and self.preferred_backend == "torch"
)