Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Add doc string for n_gpu_layers argument and make -1 offload all layers #604

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Aug 15, 2023
Merged

Add doc string for n_gpu_layers argument and make -1 offload all layers #604

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d018c7b
Add doc string for n_gpu_layers argument
aliencaocao Aug 12, 2023
c471871
make n_gpu_layers=-1 offload all layers
aliencaocao Aug 13, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion llama_cpp/llama.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -239,6 +239,7 @@ def __init__(
n_ctx: Maximum context size.
n_parts: Number of parts to split the model into. If -1, the number of parts is automatically determined.
seed: Random seed. -1 for random.
n_gpu_layers: Number of layers to offload to GPU (-ngl). If -1, all layers are offloaded.
f16_kv: Use half-precision for key/value cache.
logits_all: Return logits for all tokens, not just the last token.
vocab_only: Only load the vocabulary no weights.
Expand Down Expand Up @@ -267,7 +268,7 @@ def __init__(

self.params = llama_cpp.llama_context_default_params()
self.params.n_ctx = n_ctx
self.params.n_gpu_layers = n_gpu_layers
self.params.n_gpu_layers = 0x7FFFFFFF if n_gpu_layers == -1 else n_gpu_layers # 0x7FFFFFFF is INT32 max, will be auto set to all layers
self.params.seed = seed
self.params.f16_kv = f16_kv
self.params.logits_all = logits_all
Expand Down