Files
xc-llm-ascend/csrc/dispatch_ffn_combine/op_kernel/utils/layout3d.hpp
Chen Chen ad0607f900 add dispatch_gmm_combine kernel (#3532)
### What this PR does / why we need it?

This PR introduces the Ascend implementation of the
`dispatch_ffn_combine` kernel and wires it into the vLLM-Ascend runtime,
together with follow‑up fixes to ensure the kernel builds and runs
correctly in CI.

- Add full host and device implementation of the `dispatch_ffn_combine`
kernel under `csrc/dispatch_ffn_combine`, including tiling logic, MOE
routing helpers, and kernel utilities for quantized FFN dispatch.
- Integrate the new kernel with the PyTorch binding
(csrc/torch_binding.cpp, csrc/torch_binding_meta.cpp) and the Ascend
runtime (vllm_ascend/ascend_forward_context.py,
vllm_ascend/worker/model_runner_v1.py).
- Extend fused MoE communication and token dispatch support in
`vllm_ascend/ops/fused_moe`, adding methods/utilities needed by the new
dispatch path.
- Update quantization logic in vllm_ascend/quantization/w8a8_dynamic.py
to support the new FFN dispatch flow.
- Fix kernel build issues by adjusting `csrc/build_aclnn.sh`, CMake
configuration, and include/namespace usage in the new kernel files.
- Add an end‑to‑end nightly test
`tests/e2e/nightly/ops/test_dispatch_ffn_combine.py` and helper
utilities in `vllm_ascend/utils.py` to validate the new kernel.

### Does this PR introduce _any_ user-facing change?

### How was this patch tested?


- vLLM version: v0.12.0
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.12.0

---------

Signed-off-by: mojave2 <chenchen145@huawei.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>
2025-12-04 23:00:59 +08:00

21 lines
509 B
C++

#ifndef LAYOUT_3D_HPP
#define LAYOUT_3D_HPP
#include "kernel_operator.h"
#include "catlass/catlass.hpp"
class Layout3D {
int64_t strides[2];
public:
CATLASS_DEVICE
Layout3D() {}
CATLASS_DEVICE
Layout3D(int64_t stride0, int64_t stride1) {
strides[0] = stride0;
strides[1] = stride1;
}
CATLASS_DEVICE
int64_t operator() (int64_t dim0, int64_t dim1, int64_t dim2) {
return dim0 * strides[0] + dim1 * strides[1] + dim2;
}
};
#endif // LAYOUT_3D_HPP