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

[Bugfix] Fix triton import with local TritonPlaceholder (#17446)

Browse Source 
Signed-off-by: Mengqing Cao <cmq0113@163.com>
This commit is contained in:
Mengqing Cao
2025-05-06 17:53:09 +08:00
committed by GitHub
parent 05e1f96419
commit f9bc5a0693
30 changed files with 165 additions and 75 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
vllm/model_executor/layers/fused_moe/fused_moe.py
View File

@@ -6,8 +6,6 @@ import os
from typing import Any, Callable, Dict, List, Optional, Tuple
import torch
import triton
import triton.language as tl
import vllm.envs as envs
from vllm import _custom_ops as ops
@@ -21,6 +19,7 @@ from vllm.model_executor.layers.quantization.utils.fp8_utils import (
from vllm.model_executor.layers.quantization.utils.int8_utils import (
per_token_group_quant_int8, per_token_quant_int8)
from vllm.platforms import current_platform
from vllm.triton_utils import tl, triton
from vllm.utils import direct_register_custom_op
from .rocm_aiter_fused_moe import is_rocm_aiter_moe_enabled