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
51 lines
1.6 KiB
Python
51 lines
1.6 KiB
Python
from typing import Union
|
|
|
|
import ixformer._C as ops
|
|
import torch
|
|
|
|
__all__ = ["solve", "ref_slove"]
|
|
|
|
|
|
def ref_slove(
|
|
A: torch.Tensor, B: torch.Tensor, *, left: bool = True, out: torch.Tensor = None
|
|
):
|
|
out = torch.linalg.solve(A, B, left=left)
|
|
return out
|
|
|
|
|
|
def solve(
|
|
A: torch.Tensor, B: torch.Tensor, *, left: bool = True, out: torch.Tensor = None
|
|
):
|
|
"""
|
|
Args:
|
|
A: (..., n, n) torch.float
|
|
B: (..., n) or (..., n, k) or (n,...) or (n, k) or (n) torch.float
|
|
left: bool
|
|
whether to solve the system AX=B or XA=B. Default: True, 目前只支持left =True
|
|
out: (..., n, k) torch.float
|
|
Returns:
|
|
out: (..., n, k) torch.float
|
|
"""
|
|
|
|
n = A.shape[-1]
|
|
batch_count = A.numel() // (n * n)
|
|
if B.dim() == 1:
|
|
k = 1
|
|
elif B.dim() == 2:
|
|
if A.dim() > 2 and B.shape == (batch_count, n):
|
|
k = 1
|
|
else:
|
|
nid = 0 if left else 1
|
|
k = B.shape[nid ^ 1]
|
|
else:
|
|
k = B.size(B.dim() - 1 if left else B.dim() - 2)
|
|
|
|
if n <= 64 and k <= 64 and left:
|
|
return ops.infer.solve(A, B, left)
|
|
else:
|
|
device = A.device
|
|
cpu_A = A.cpu()
|
|
cpu_B = B.cpu()
|
|
cpu_res = ref_slove(A=cpu_A, B=cpu_B, left=left)
|
|
return cpu_res.to(device)
|