xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-03-26 02:24:44 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge ac23d0ba18407d09501fe470573940b63129964f into 254f6b986720c92ddf97fbb1a6a6465da8e87e29

Browse Source
This commit is contained in:
Kevin McKay 2025-12-25 00:07:06 +00:00 committed by GitHub
commit e28a0c8fb2
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 7 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
csrc/sampler.cu
View File

@ -1,3 +1,4 @@
#include "cuda_compat.h"
#include "dispatch_utils.h"
#include <torch/cuda.h>
@ -97,7 +98,9 @@ static inline __device__ bool isPartialMatch(float x, uint32_t pattern) {
template <typename T, typename idxT, typename Func>
__device__ void vectorized_process(size_t thread_rank, size_t num_threads,
const T* in, idxT len, Func f) {
constexpr int WARP_SIZE = 32;
// Use dynamic WARP_SIZE from cuda_compat.h to support both
// Wave64 (MI300X/gfx942) and Wave32 (Strix Halo/gfx1151) architectures
constexpr int kWarpSize = WARP_SIZE;
using WideT = float4;
if constexpr (sizeof(T) >= sizeof(WideT)) {
for (idxT i = thread_rank; i < len; i += num_threads) {
@ -132,8 +135,8 @@ __device__ void vectorized_process(size_t thread_rank, size_t num_threads,
}
}
static_assert(WARP_SIZE >= items_per_scalar);
// and because items_per_scalar > skip_cnt, WARP_SIZE > skip_cnt
static_assert(kWarpSize >= items_per_scalar);
// and because items_per_scalar > skip_cnt, kWarpSize > skip_cnt
// no need to use loop
if (thread_rank < skip_cnt) {
f(in[thread_rank], thread_rank);
@ -142,7 +145,7 @@ __device__ void vectorized_process(size_t thread_rank, size_t num_threads,
// len_cast * items_per_scalar + items_per_scalar > len - skip_cnt;
// and so
// len - (skip_cnt + len_cast * items_per_scalar) < items_per_scalar <=
// WARP_SIZE no need to use loop
// kWarpSize no need to use loop
const idxT remain_i = skip_cnt + len_cast * items_per_scalar + thread_rank;
if (remain_i < len) {
f(in[remain_i], remain_i);