Asep Haryana
e1f5195407
- Token-by-token streaming via Server-Sent Events - tokio::sync::mpsc channel + ReceiverStream for clean async - OpenAI SSE format: role chunk → content chunks → finish chunk - Non-streaming still works with the same code path - Uses spawn_blocking pattern for CPU-bound inference
27 lines
612 B
TOML
27 lines
612 B
TOML
[package]
|
|
name = "llm-api"
|
|
version = "0.1.0"
|
|
edition = "2021"
|
|
|
|
[dependencies]
|
|
# LLM inference
|
|
llama-cpp-2 = "0.1"
|
|
|
|
# HTTP server
|
|
axum = { version = "0.8", features = ["json"] }
|
|
tokio = { version = "1", features = ["full"] }
|
|
tokio-stream = "0.1"
|
|
tower-http = { version = "0.6", features = ["cors", "trace"] }
|
|
|
|
# Serialization
|
|
serde = { version = "1", features = ["derive"] }
|
|
serde_json = "1"
|
|
|
|
# Utilities
|
|
tracing = "0.1"
|
|
tracing-subscriber = { version = "0.3", features = ["env-filter"] }
|
|
anyhow = "1"
|
|
uuid = { version = "1", features = ["v4"] }
|
|
chrono = { version = "0.4", features = ["serde"] }
|
|
futures = "0.3"
|