Skip to content

Device option sep #1397

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

Open
genrtul wants to merge 7 commits into
base: main
Choose a base branch
from
Open

Device option sep #1397

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
7dae5f4
Separated out --device option for llamacpp backend
Mar 18, 2026
ea1f372
Checked for empty
Mar 18, 2026
b566a6e
Change help doc to acknowledge commas
Mar 18, 2026
5b80656
Docs changes
Mar 20, 2026
2891d42
Implement suggestions: always reserve flag and change flag name
Mar 20, 2026
e192ec6
Merge branch 'lemonade-sdk:main' into device-option-sep
genrtul Mar 25, 2026
0c1208d
Fix flag name
Mar 25, 2026
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
4 changes: 4 additions & 0 deletions src/cpp/server/backends/llamacpp_server.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -158,6 +158,7 @@ void LlamaCppServer::load(const std::string& model_name,
LOG(DEBUG, "LlamaCpp") << "Per-model settings: " << options.to_log_string() << std::endl;

int ctx_size = options.get_option("ctx_size");
std::string backend_device = options.get_option("device");
std::string llamacpp_backend = options.get_option("llamacpp_backend");
std::string llamacpp_args = options.get_option("llamacpp_args");

Expand Down Expand Up @@ -200,6 +201,9 @@ void LlamaCppServer::load(const std::string& model_name,

push_arg(args, reserved_flags, "-m", gguf_path, std::vector<std::string>{"--model"});
push_arg(args, reserved_flags, "--ctx-size", std::to_string(ctx_size), std::vector<std::string>{"-c"});
if (backend_device != "") {
push_arg(args, reserved_flags, "--device", backend_device);
}
push_arg(args, reserved_flags, "--port", std::to_string(port_));
push_arg(args, reserved_flags, "--jinja", std::vector<std::string>{"--no-jinja"});

Expand Down
9 changes: 8 additions & 1 deletion src/cpp/server/recipe_options.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,7 @@ using json = nlohmann::json;

static const json DEFAULTS = {
{"ctx_size", 4096},
{"device", ""},
{"llamacpp_backend", ""}, // Will be overridden dynamically
{"llamacpp_args", ""},
{"sd-cpp_backend", ""}, // sd.cpp backend selection (cpu or rocm)
Expand All @@ -32,6 +33,12 @@ static const json CLI_OPTIONS = {
{"envname", "LEMONADE_CTX_SIZE"},
{"help", "Context size for the model"}
}},
{"--device", {
{"option_name", "device"},
{"type_name", "DEVICE"},
{"envname", "LEMONADE_DEVICE"},
{"help", "Comma-separated list of accelerator devices to use (e.g. Vulkan0)"}
}},
{"--llamacpp", {
{"option_name", "llamacpp_backend"},
{"type_name", "BACKEND"},
Expand Down Expand Up @@ -100,7 +107,7 @@ static const json CLI_OPTIONS = {

static std::vector<std::string> get_keys_for_recipe(const std::string& recipe) {
if (recipe == "llamacpp") {
return {"ctx_size", "llamacpp_backend", "llamacpp_args"};
return {"ctx_size", "device", "llamacpp_backend", "llamacpp_args"};
} else if (recipe == "whispercpp") {
return {"whispercpp_backend", "whispercpp_args"};
} else if (recipe == "flm") {
Expand Down
Loading