vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

backend : offload large batches to GPU (#6083)

Browse source 
* backend : offload large batches to GPU

* fix hip

* code cleanup

* fix CUDA split buffers

* Update ggml-backend-impl.h

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

* cuda : fix memset without set_device

* imatrix : remove sched affix from weight names

* sched : add a new split if the current one has too many inputs
reduce max inputs per split
more cleanup

* update backends

ggml-ci

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
This commit is contained in:
slaren 2024-03-18 11:03:04 +01:00 • committed by GitHub
parent 496bc79bc2
commit 2bf8d0f7c4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
14 changed files with 349 additions and 396 deletions
Download patch file Download diff file Expand all files Collapse all files

4
examples/llama-bench/llama-bench.cpp
View file

@ -114,10 +114,10 @@ static std::string get_cpu_info() {
static std::string get_gpu_info() {
std::string id;
#ifdef GGML_USE_CUBLAS
int count = ggml_cuda_get_device_count();
int count = ggml_backend_cuda_get_device_count();
for (int i = 0; i < count; i++) {
char buf[128];
ggml_cuda_get_device_description(i, buf, sizeof(buf));
ggml_backend_cuda_get_device_description(i, buf, sizeof(buf));
id += buf;
if (i < count - 1) {
id += "/";