biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Merge EmbeddedLLM/vllm-rocm into vLLM main (#1836)

Browse Source 
Co-authored-by: Philipp Moritz <pcmoritz@gmail.com>
Co-authored-by: Amir Balwel <amoooori04@gmail.com>
Co-authored-by: root <kuanfu.liu@akirakan.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: kuanfu <kuanfu.liu@embeddedllm.com>
Co-authored-by: miloice <17350011+kliuae@users.noreply.github.com>
This commit is contained in:
TJian
2023-12-08 15:16:52 +08:00
committed by GitHub
parent c8e7eb1eb3
commit 6ccc0bfffb
29 changed files with 873 additions and 118 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
csrc/activation_kernels.cu
View File

@@ -1,6 +1,7 @@
#include <torch/extension.h>
#include <ATen/cuda/CUDAContext.h>
#include "cuda_compat.h"
#include "dispatch_utils.h"
namespace vllm {
@@ -18,8 +19,8 @@ __global__ void silu_and_mul_kernel(
const int d) {
const int64_t token_idx = blockIdx.x;
for (int64_t idx = threadIdx.x; idx < d; idx += blockDim.x) {
const scalar_t x = __ldg(&input[token_idx * 2 * d + idx]);
const scalar_t y = __ldg(&input[token_idx * 2 * d + d + idx]);
const scalar_t x = VLLM_LDG(&input[token_idx * 2 * d + idx]);
const scalar_t y = VLLM_LDG(&input[token_idx * 2 * d + d + idx]);
out[token_idx * d + idx] = silu(x) * y;
}
}
@@ -57,7 +58,7 @@ __global__ void activation_kernel(
const int d) {
const int64_t token_idx = blockIdx.x;
for (int64_t idx = threadIdx.x; idx < d; idx += blockDim.x) {
const scalar_t x = __ldg(&input[token_idx * d + idx]);
const scalar_t x = VLLM_LDG(&input[token_idx * d + idx]);
out[token_idx * d + idx] = ACT_FN(x);
}
}