From cfd22726c914285c9f9036695f9e80112d854c70 Mon Sep 17 00:00:00 2001 From: Morgan Funtowicz Date: Tue, 21 Jan 2025 23:37:56 +0100 Subject: [PATCH] backend(vllm): initial commit --- Cargo.lock | 6 +++++- Cargo.toml | 7 +++++-- backends/vllm/Cargo.toml | 10 ++++++++++ backends/vllm/src/main.rs | 6 ++++++ 4 files changed, 26 insertions(+), 3 deletions(-) create mode 100644 backends/vllm/Cargo.toml create mode 100644 backends/vllm/src/main.rs diff --git a/Cargo.lock b/Cargo.lock index e63d1540..0059976b 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -1,6 +1,6 @@ # This file is automatically @generated by Cargo. # It is not intended for manual editing. -version = 3 +version = 4 [[package]] name = "addr2line" @@ -4443,6 +4443,10 @@ dependencies = [ "tracing", ] +[[package]] +name = "text-generation-backends-vllm" +version = "3.0.2-dev0" + [[package]] name = "text-generation-benchmark" version = "3.0.2-dev0" diff --git a/Cargo.toml b/Cargo.toml index 9f49c9ab..4183614e 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -5,15 +5,18 @@ members = [ "backends/v3", "backends/grpc-metadata", "backends/trtllm", + "backends/vllm", "launcher", - "router" + "router", ] + default-members = [ "benchmark", "backends/v2", "backends/v3", "backends/grpc-metadata", # "backends/trtllm", + # "backends/vllm", "launcher", "router" ] @@ -33,7 +36,7 @@ metrics = { version = "0.23.0" } metrics-exporter-prometheus = { version = "0.15.1", features = [] } minijinja = { version = "2.2.0", features = ["json"] } minijinja-contrib = { version = "2.0.2", features = ["pycompat"] } -pyo3 = { version = "0.22.2", features = ["auto-initialize"] } +pyo3 = { version = "0.23", features = ["auto-initialize"] } [profile.release] incremental = true diff --git a/backends/vllm/Cargo.toml b/backends/vllm/Cargo.toml new file mode 100644 index 00000000..b738745e --- /dev/null +++ b/backends/vllm/Cargo.toml @@ -0,0 +1,10 @@ +[package] +name = "text-generation-backends-vllm" +version.workspace = true +edition.workspace = true +authors.workspace = true +homepage.workspace = true + +[dependencies] +pyo3 = "0.23" +pyo3-asyncio = "0.20" \ No newline at end of file diff --git a/backends/vllm/src/main.rs b/backends/vllm/src/main.rs new file mode 100644 index 00000000..fd54d8b1 --- /dev/null +++ b/backends/vllm/src/main.rs @@ -0,0 +1,6 @@ +use pyo3::prelude::*; + +#[pyo3_asyncio::tokio::main(flavor = "multi_thread")] +async fn main() { + println!("Hello, world!"); +}