87a19d2d00
来源:
1. Chranos/ixformer (GitHub) → ixformer_sdk/ (230 files, 70K lines)
- inference/functions/vllm.py: vllm_moe_topk_softmax 完整实现 (2033 lines)
- inference/functions/moe.py: MoE ops 完整实现 (1380 lines)
- contrib/vllm_flash_attn/: FA2 Python 接口 (1018 lines)
- contrib/tgi/fused_moe.py: TGI fused MoE (429 lines)
- csrc/include/ixformer/: C++ kernel headers + cmake
2. Deep-Spark/xllm (GitHub) → upstream_ref/xllm_latest/ (+15 files)
- npu_torch/qwen3_5_decoder_layer_impl.cpp/.h
- npu_torch/qwen3_5_gated_delta_net.cpp/.h
- npu_torch/qwen3_next_*.cpp/.h (6 files)
- npu_torch/attention.cpp/.h + fused_moe.cpp/.h + CMakeLists.txt
- models/llm/qwen3_5.h + qwen3_5_mtp.h + qwen3_next.h
- models/vlm/qwen3_5.h
调用链完整性:
ixformer_sdk/inference/functions/vllm.py
→ ops.infer.moe_topk_softmax() (C++ 层)
→ 这就是 base 镜像 libixformer.so 里的实现
upstream_ref/xllm_latest/core/layers/ilu/fused_moe.cpp
→ ixformer::infer::topk_softmax() (直接 C++ 调用)
→ ixformer::infer::group_gemm() → 完整 7-step MoE pipeline
49 lines
1.5 KiB
Python
49 lines
1.5 KiB
Python
import os
|
|
from typing import Union
|
|
|
|
import ixformer._C as ops
|
|
import torch
|
|
|
|
__all__ = ["gemv", "ref_gemv"]
|
|
|
|
|
|
def ref_gemv(x: torch.Tensor, A: torch.Tensor, gemv_max_batch: int = 1):
|
|
output = torch.nn.functional.linear(x, A)
|
|
return output
|
|
|
|
|
|
def gemv_conditions(input, weight, gemv_max_batch):
|
|
# gemv 使用的条件 input:[m,k] weight:[n,k]
|
|
# 1. m<=gemv_max_batch
|
|
# 2. k%2==0 n%2==0
|
|
# 3. bias is None
|
|
input = input.view(-1, input.shape[-1])
|
|
weight = weight.view(-1, weight.shape[-1])
|
|
m = input.shape[0]
|
|
k = input.shape[1]
|
|
n = weight.shape[0]
|
|
if m <= gemv_max_batch and k % 2 == 0 and n % 2 == 0:
|
|
return True
|
|
return False
|
|
|
|
|
|
def gemv(x: torch.Tensor, A: torch.Tensor, gemv_max_batch: int = 1):
|
|
|
|
"""
|
|
Args:
|
|
x: (..., k) torch.float16, torch.bfloat16
|
|
A: (n,k) torch.float16, torch.bfloat16, torch.float32
|
|
gemv_max_batch: int
|
|
用于是否满足gemv使用条件的判断,目前只支持到1
|
|
Returns:
|
|
Tensor: (..., n) torch.float16, torch.bfloat16
|
|
"""
|
|
disable_infer_gemm_ex = os.getenv("DISABLE_INFER_GEMM_EX", "0")
|
|
use_gemv = gemv_conditions(x, A, gemv_max_batch) and disable_infer_gemm_ex != "1"
|
|
assert use_gemv == True
|
|
output_shape = list(x.shape)
|
|
output_shape[-1] = A.shape[0]
|
|
output = x.new_empty(output_shape)
|
|
output = ops.infer.linear_ex(x, A, None, output)
|
|
return output
|