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

llama : accept a list of devices to use to offload a model (#10497)

Browse source 
* llama : accept a list of devices to use to offload a model

* accept `--dev none` to completely disable offloading

* fix dev list with dl backends

* rename env parameter to LLAMA_ARG_DEVICE for consistency
This commit is contained in:
Diego Devesa 2024-11-25 19:30:06 +01:00 • committed by GitHub
parent 1f922254f0
commit 10bce0450f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 104 additions and 27 deletions
Download patch file Download diff file Expand all files Collapse all files

1
examples/server/server.cpp
View file

@ -692,6 +692,7 @@ struct server_context {
auto params_dft = params_base;
params_dft.devices = params_base.speculative.devices;
params_dft.model = params_base.speculative.model;
params_dft.n_ctx = params_base.speculative.n_ctx;
params_dft.n_gpu_layers = params_base.speculative.n_gpu_layers;

1
examples/speculative-simple/speculative-simple.cpp
View file

@ -46,6 +46,7 @@ int main(int argc, char ** argv) {
ctx_tgt = llama_init_tgt.context;
// load the draft model
params.devices = params.speculative.devices;
params.model = params.speculative.model;
params.n_ctx = params.speculative.n_ctx;
params.n_batch = params.speculative.n_ctx > 0 ? params.speculative.n_ctx : params.n_batch;

1
examples/speculative/speculative.cpp
View file

@ -76,6 +76,7 @@ int main(int argc, char ** argv) {
ctx_tgt = llama_init_tgt.context;
// load the draft model
params.devices = params.speculative.devices;
params.model = params.speculative.model;
params.n_gpu_layers = params.speculative.n_gpu_layers;
if (params.speculative.cpuparams.n_threads > 0) {