frozenleaves/vllm
1
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2025-10-20 14:53:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

Handle triton kernel import exception (#25319)

Browse Source 
Signed-off-by: Ming Yang <minos.future@gmail.com>
This commit is contained in:
Ming Yang
2025-09-23 00:56:00 -07:00
committed by GitHub
parent c98be0a232
commit ba8d2165b6
1 changed files with 8 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
vllm/model_executor/layers/fused_moe/config.py
View File

@ -14,11 +14,16 @@ from vllm.model_executor.layers.quantization.utils.quant_utils import (
from vllm.utils import cdiv, has_triton_kernels
from vllm.utils.flashinfer import has_flashinfer_cutlass_fused_moe
if has_triton_kernels():
from triton_kernels.matmul_ogs import PrecisionConfig
logger = init_logger(__name__)
if has_triton_kernels():
try:
from triton_kernels.matmul_ogs import PrecisionConfig
except ImportError:
logger.error(
"Failed to import Triton kernels. Please make sure your triton "
"version is compatible.")
def _get_config_dtype_str(
dtype: torch.dtype,