Skip to content
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

feat: tokenization with llama.cpp #4724

Merged
merged 1 commit into from
Feb 2, 2025
Merged

feat: tokenization with llama.cpp #4724

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
12 changes: 12 additions & 0 deletions backend/cpp/llama/grpc-server.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2542,6 +2542,18 @@ class BackendServiceImpl final : public backend::Backend::Service {
return grpc::Status::OK;
}

grpc::Status TokenizeString(ServerContext* context, const backend::PredictOptions* request, backend::TokenizationResponse* response){
json data = parse_options(false, request, llama);

std::vector<llama_token> tokens = llama.tokenize(data["prompt"],false);

for (int i=0 ; i< tokens.size(); i++){
response->add_tokens(tokens[i]);
}

return grpc::Status::OK;
}

grpc::Status GetMetrics(ServerContext* context, const backend::MetricsRequest* request, backend::MetricsResponse* response) {
llama_client_slot* active_slot = llama.get_active_slot();

Expand Down
11 changes: 5 additions & 6 deletions core/backend/tokenize.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,12 +16,7 @@ func ModelTokenize(s string, loader *model.ModelLoader, backendConfig config.Bac

opts := ModelOptions(backendConfig, appConfig, model.WithModel(modelFile))

if backendConfig.Backend == "" {
inferenceModel, err = loader.Load(opts...)
} else {
opts = append(opts, model.WithBackendString(backendConfig.Backend))
inferenceModel, err = loader.Load(opts...)
}
inferenceModel, err = loader.Load(opts...)
if err != nil {
return schema.TokenizeResponse{}, err
}
Expand All @@ -35,6 +30,10 @@ func ModelTokenize(s string, loader *model.ModelLoader, backendConfig config.Bac
return schema.TokenizeResponse{}, err
}

if resp.Tokens == nil {
resp.Tokens = make([]int32, 0)
}

return schema.TokenizeResponse{
Tokens: resp.Tokens,
}, nil
Expand Down
5 changes: 2 additions & 3 deletions core/http/endpoints/localai/tokenize.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,7 @@ import (

// TokenizeEndpoint exposes a REST API to tokenize the content
// @Summary Tokenize the input.
// @Param request body schema.TokenizeRequest true "Request"
// @Success 200 {object} schema.TokenizeResponse "Response"
// @Router /v1/tokenize [post]
func TokenizeEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, appConfig *config.ApplicationConfig) func(c *fiber.Ctx) error {
Expand Down Expand Up @@ -51,8 +52,6 @@ func TokenizeEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, app
return err
}

c.JSON(tokenResponse)
return nil

return c.JSON(tokenResponse)
}
}
Loading