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
47 lines
1.5 KiB
Python
47 lines
1.5 KiB
Python
import ixformer._C as ops
|
|
import torch
|
|
|
|
__all__ = [
|
|
"ref_add",
|
|
"add",
|
|
]
|
|
|
|
|
|
def ref_add(input: torch.Tensor, other: torch.Tensor, out: torch.Tensor = None):
|
|
return torch.add(input, other, out=out)
|
|
|
|
|
|
def add(input: torch.Tensor, other: torch.Tensor, out: torch.Tensor = None):
|
|
"""
|
|
out = input + other
|
|
Support elementwise addition, but broadcasting is not supported yet.
|
|
Note: The dtype of input and other needs to be the same.
|
|
Args:
|
|
input: (...) torch.float32, torch.float16, torch.bfloat16
|
|
other: (...) same as input
|
|
out: (...) same as input
|
|
Returns:
|
|
out: (...) same as input
|
|
"""
|
|
if input.dtype not in [torch.float16, torch.float32, torch.bfloat16]:
|
|
return torch.add(input, other, out=out)
|
|
if not input.is_contiguous() or not other.is_contiguous():
|
|
return torch.add(input, other, out=out)
|
|
if out is not None and not out.is_contiguous():
|
|
return torch.add(input, other, out=out)
|
|
|
|
if input.dtype != other.dtype:
|
|
return torch.add(input, other, out=out)
|
|
if out is not None and out.dtype != input.dtype:
|
|
return torch.add(input, other, out=out)
|
|
|
|
assert input.shape == other.shape, (f"broadcasting is not supported yet."
|
|
"input is {input.shape}, other is {other.shape}")
|
|
|
|
if out is None:
|
|
out = torch.empty_like(input)
|
|
|
|
ops.infer.add(input, other, out)
|
|
|
|
return out
|