tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-28 19:18:57 -04:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: faster q2_K, q3_K MMQ + int8 tensor cores (#7921)

Browse Source 
* CUDA: faster q2_K, q3_K MMQ + int8 tensor cores

* try CI fix

* try CI fix

* try CI fix

* fix data race

* rever q2_K precision related changes
This commit is contained in:
Johannes Gäßler
2024-06-14 18:41:49 +02:00
committed by GitHub
parent 66ef1ceedf
commit 76d66ee0be
6 changed files with 468 additions and 330 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
ggml-cuda.cu
View File

@@ -188,13 +188,15 @@ static ggml_cuda_device_info ggml_cuda_init() {
info.default_tensor_split[id] = total_vram;
total_vram += prop.totalGlobalMem;
info.devices[id].nsm = prop.multiProcessorCount;
info.devices[id].smpb = prop.sharedMemPerBlock;
#if defined(GGML_USE_HIPBLAS) && defined(__HIP_PLATFORM_AMD__)
info.devices[id].smpbo = prop.sharedMemPerBlock;
info.devices[id].cc = 100*prop.major + 10*prop.minor + CC_OFFSET_AMD;
#else
info.devices[id].smpbo = prop.sharedMemPerBlockOptin;
info.devices[id].cc = 100*prop.major + 10*prop.minor;
#endif // defined(GGML_USE_HIPBLAS) && defined(__HIP_PLATFORM_AMD__)
info.devices[id].smpb = prop.sharedMemPerBlock;
info.devices[id].nsm = prop.multiProcessorCount;
}
for (int id = 0; id < info.device_count; ++id) {