nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 35 Packages Projects Releases Wiki Activity

Avoid PDL race conditions by disabling __restrict__ when PDL is used (#24030)

Browse Source 
* Removes __restrict__ from PDL kernel headers due to incompatibility with
PDL. Adds preprocessor directives based on arch in kernel body to add
__restrict__ to retain performance on older architectures.

* Simplifies new __restrict__ usage via macro

* Add hopper to PDL __restrict__ fix.

Co-authored-by: Oliver Simons <osimons@nvidia.com>

---------

Co-authored-by: Oliver Simons <osimons@nvidia.com>
This commit is contained in:
Andreas Kieslinger
2026-06-03 13:56:42 +02:00
committed by GitHub
co-authored by Oliver Simons
parent 3571fa5435
commit 9e58d4d692
14 changed files with 145 additions and 62 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cuda/mmvq.cu
+5 -1
View File
@@ -476,12 +476,16 @@ static constexpr __host__ __device__ int calc_rows_per_block(int ncols_dst, int
template <ggml_type type, int ncols_dst, bool has_fusion, bool small_k = false>
__launch_bounds__(calc_nwarps(type, ncols_dst, get_device_table_id())*ggml_cuda_get_physical_warp_size(), 1)
static __global__ void mul_mat_vec_q(
const void * __restrict__ vx, const void * __restrict__ vy, const int32_t * __restrict__ ids, const ggml_cuda_mm_fusion_args_device fusion, float * __restrict__ dst,
const void * vx_ptr, const void * vy_ptr, const int32_t * ids_ptr, const ggml_cuda_mm_fusion_args_device fusion, float * dst_ptr,
const uint32_t ncols_x, const uint3 nchannels_y, const uint32_t stride_row_x, const uint32_t stride_col_y,
const uint32_t stride_col_dst, const uint3 channel_ratio, const uint32_t stride_channel_x,
const uint32_t stride_channel_y, const uint32_t stride_channel_dst, const uint3 sample_ratio,
const uint32_t stride_sample_x, const uint32_t stride_sample_y, const uint32_t stride_sample_dst,
const uint32_t ids_stride) {
const void * GGML_CUDA_RESTRICT vx = vx_ptr;
const void * GGML_CUDA_RESTRICT vy = vy_ptr;
const int32_t * GGML_CUDA_RESTRICT ids = ids_ptr;
float * GGML_CUDA_RESTRICT dst = dst_ptr;
constexpr int qk = ggml_cuda_type_traits<type>::qk;
constexpr int qi = ggml_cuda_type_traits<type>::qi;