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

llama : remove LLAMA_MAX_DEVICES and LLAMA_SUPPORTS_GPU_OFFLOAD (#5240)

Browse source 
* llama : remove LLAMA_MAX_DEVICES from llama.h

ggml-ci

* Update llama.cpp

Co-authored-by: slaren <slarengh@gmail.com>

* server : remove LLAMA_MAX_DEVICES

ggml-ci

* llama : remove LLAMA_SUPPORTS_GPU_OFFLOAD

ggml-ci

* train : remove LLAMA_SUPPORTS_GPU_OFFLOAD

* readme : add deprecation notice

* readme : change deprecation notice to "remove" and fix url

* llama : remove gpu includes from llama.h

ggml-ci

---------

Co-authored-by: slaren <slarengh@gmail.com>
This commit is contained in:
Georgi Gerganov 2024-01-31 17:30:17 +02:00 • committed by GitHub
parent efb7bdbbd0
commit 5cb04dbc16
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 143 additions and 124 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/batched-bench/batched-bench.cpp
View file

@ -88,7 +88,7 @@ int main(int argc, char ** argv) {
llama_model_params model_params = llama_model_default_params();
const std::vector<float> t_split (LLAMA_MAX_DEVICES, 0.0f);
const std::vector<float> t_split(llama_max_devices(), 0.0f);
model_params.n_gpu_layers = n_gpu_layers;
model_params.tensor_split = t_split.data();