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
59 lines
1.6 KiB
Python
59 lines
1.6 KiB
Python
from typing import List, Union
|
|
|
|
import ixformer._C as ops
|
|
import torch
|
|
|
|
__all__ = ["bnb_quant", "ref_bnb_quant"]
|
|
|
|
|
|
# A : input shape : [row, col]
|
|
# SA : scale vector
|
|
# quant_type
|
|
# 0 : every row shared a scale, SA shape : [row]
|
|
# 1 : every col shared a scale, SA shape : [col]
|
|
def ref_bnb_quant(
|
|
A: torch.Tensor,
|
|
SA: torch.Tensor,
|
|
training: bool = False,
|
|
scale: float = 127.0,
|
|
quant_type: int = 0,
|
|
):
|
|
qA = torch.empty(A.shape, device = SA.device)
|
|
if quant_type == 0:
|
|
for i in range(A.size(0)):
|
|
qA[i:] = torch.round(A[i:] * (scale / SA[i].to(torch.float)))
|
|
else:
|
|
for i in range(A.size(1)):
|
|
qA[:,i] = torch.round(A[:,i] * (scale / SA[i].to(torch.float)))
|
|
|
|
qA_clamped = torch.clamp(qA, min=-128, max=127)
|
|
qA = qA_clamped.to(torch.int8)
|
|
return qA
|
|
|
|
|
|
def bnb_quant(
|
|
A: torch.Tensor,
|
|
SA: torch.Tensor,
|
|
training: bool = False,
|
|
scale: float = 127.0,
|
|
quant_type: int = 0,
|
|
) -> torch.Tensor:
|
|
|
|
"""
|
|
Args:
|
|
A: (row, col) torch.half
|
|
quant input
|
|
SA: (row) or (col) torch.half
|
|
scale vector
|
|
training: bool
|
|
scale: float
|
|
qunt_type: int
|
|
0 : every row shared a scale, SA shape : [row]
|
|
1 : every col shared a scale, SA shape : [col]
|
|
Returns:
|
|
Tensor: (row, col) torch.int8
|
|
quant output
|
|
|
|
"""
|
|
return ops.infer.bnb_quant(A, SA, scale, quant_type)
|