ROCm: sgl-kernel enablement starting with sgl_moe_align_block (#3287)

This commit is contained in:
HAI
2025-02-04 05:44:44 -08:00
committed by GitHub
parent d39899e85c
commit 2c1a695ff1
6 changed files with 131 additions and 13 deletions

View File

@@ -0,0 +1,29 @@
/* Copyright 2025 SGLang Team. All Rights Reserved.
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
==============================================================================*/
#include <ATen/core/dispatch/Dispatcher.h>
#include <torch/library.h>
#include "sgl_kernels_ops.h"
TORCH_LIBRARY_EXPAND(sgl_kernels, m) {
// moe_align_block_size
m.def(
"moe_align_block_size(Tensor topk_ids, int num_experts, int block_size, Tensor! sorted_token_ids, Tensor! "
"experts_ids, Tensor! num_tokens_post_pad, Tensor! token_cnts_buffer, Tensor! cumsum_buffer) -> ()");
m.impl("moe_align_block_size", torch::kCUDA, &moe_align_block_size);
}
REGISTER_EXTENSION(_kernels)