ad0607f900
### 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>
73 lines
3.0 KiB
C++
73 lines
3.0 KiB
C++
/* Copyright (c) 2025 Huawei Technologies Co., Ltd.
|
|
* This file is a part of the CANN Open Software.
|
|
* Licensed under CANN Open Software License Agreement Version 1.0 (the "License").
|
|
* Please refer to the License for details. You may not use this file except in compliance with the License.
|
|
* THIS SOFTWARE IS PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, EITHER EXPRESS OR IMPLIED,
|
|
* INCLUDING BUT NOT LIMITED TO NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE.
|
|
* See LICENSE in the root of the software repository for the full text of the License.
|
|
* ===================================================================================================================*/
|
|
|
|
#ifndef METADEF_CXX_INC_EXTERNAL_HCOM_HCOM_TOPO_INFO_H_
|
|
#define METADEF_CXX_INC_EXTERNAL_HCOM_HCOM_TOPO_INFO_H_
|
|
|
|
#include <unordered_map>
|
|
#include <mutex>
|
|
|
|
using Status = int32_t;
|
|
|
|
namespace ge {
|
|
static constexpr uint32_t COMM_MESH = 0b1U;
|
|
static constexpr uint32_t COMM_SWITCH = (COMM_MESH << 1U);
|
|
static constexpr uint32_t COMM_RING = (COMM_MESH << 2U);
|
|
static constexpr uint32_t COMM_PAIRWISE = (COMM_MESH << 3U);
|
|
class HcomTopoInfo {
|
|
public:
|
|
enum class TopoLevel {
|
|
L0 = 0,
|
|
L1,
|
|
MAX,
|
|
};
|
|
struct TopoLevelDesc {
|
|
uint32_t comm_sets;
|
|
uint32_t rank_size;
|
|
};
|
|
using TopoDescs = TopoLevelDesc[static_cast<int32_t>(TopoLevel::MAX)];
|
|
struct TopoInfo {
|
|
int64_t rank_size;
|
|
void *notify_handle;
|
|
TopoDescs topo_level_descs;
|
|
};
|
|
static HcomTopoInfo &Instance();
|
|
bool TopoInfoHasBeenSet(const char_t *group);
|
|
bool TryGetGroupTopoInfo(const char_t *group, TopoInfo &info);
|
|
Status SetGroupTopoInfo(const char_t *group, const TopoInfo &info);
|
|
Status GetGroupRankSize(const char_t *group, int64_t &rank_size);
|
|
TopoDescs *GetGroupTopoDesc(const char_t *group);
|
|
Status GetGroupNotifyHandle(const char_t *group, void *¬ify_handle);
|
|
void UnsetGroupTopoInfo(const char_t *group) {
|
|
const std::lock_guard<std::mutex> lock(mutex_);
|
|
(void) rank_info_.erase(group);
|
|
}
|
|
|
|
Status SetGroupOrderedStream(const char_t *group, void *stream);
|
|
Status GetGroupOrderedStream(const char_t *group, void *&stream);
|
|
void UnsetGroupOrderedStream(const char_t *group) {
|
|
const std::lock_guard<std::mutex> lock(mutex_);
|
|
(void) group_to_ordered_stream_.erase(group);
|
|
};
|
|
|
|
Status SetGroupOrderedStream(const int32_t device_id, const char_t *group, void *stream);
|
|
Status GetGroupOrderedStream(const int32_t device_id, const char_t *group, void *&stream);
|
|
void UnsetGroupOrderedStream(const int32_t device_id, const char_t *group);
|
|
private:
|
|
HcomTopoInfo() = default;
|
|
~HcomTopoInfo() = default;
|
|
std::unordered_map<std::string, TopoInfo> rank_info_;
|
|
std::mutex mutex_;
|
|
std::unordered_map<std::string, void*> group_to_ordered_stream_; // 通信域保序流
|
|
std::unordered_map<int32_t, std::unordered_map<std::string, void*>> device_id_to_group_to_ordered_stream_; // 通信域保序流
|
|
};
|
|
}
|
|
|
|
#endif // METADEF_CXX_INC_EXTERNAL_HCOM_HCOM_TOPO_INFO_H_
|