mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-23 16:02:10 +00:00
backend(vllm): initial commit
This commit is contained in:
parent
64a33c1f05
commit
cfd22726c9
6
Cargo.lock
generated
6
Cargo.lock
generated
@ -1,6 +1,6 @@
|
|||||||
# This file is automatically @generated by Cargo.
|
# This file is automatically @generated by Cargo.
|
||||||
# It is not intended for manual editing.
|
# It is not intended for manual editing.
|
||||||
version = 3
|
version = 4
|
||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "addr2line"
|
name = "addr2line"
|
||||||
@ -4443,6 +4443,10 @@ dependencies = [
|
|||||||
"tracing",
|
"tracing",
|
||||||
]
|
]
|
||||||
|
|
||||||
|
[[package]]
|
||||||
|
name = "text-generation-backends-vllm"
|
||||||
|
version = "3.0.2-dev0"
|
||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "text-generation-benchmark"
|
name = "text-generation-benchmark"
|
||||||
version = "3.0.2-dev0"
|
version = "3.0.2-dev0"
|
||||||
|
@ -5,15 +5,18 @@ members = [
|
|||||||
"backends/v3",
|
"backends/v3",
|
||||||
"backends/grpc-metadata",
|
"backends/grpc-metadata",
|
||||||
"backends/trtllm",
|
"backends/trtllm",
|
||||||
|
"backends/vllm",
|
||||||
"launcher",
|
"launcher",
|
||||||
"router"
|
"router",
|
||||||
]
|
]
|
||||||
|
|
||||||
default-members = [
|
default-members = [
|
||||||
"benchmark",
|
"benchmark",
|
||||||
"backends/v2",
|
"backends/v2",
|
||||||
"backends/v3",
|
"backends/v3",
|
||||||
"backends/grpc-metadata",
|
"backends/grpc-metadata",
|
||||||
# "backends/trtllm",
|
# "backends/trtllm",
|
||||||
|
# "backends/vllm",
|
||||||
"launcher",
|
"launcher",
|
||||||
"router"
|
"router"
|
||||||
]
|
]
|
||||||
@ -33,7 +36,7 @@ metrics = { version = "0.23.0" }
|
|||||||
metrics-exporter-prometheus = { version = "0.15.1", features = [] }
|
metrics-exporter-prometheus = { version = "0.15.1", features = [] }
|
||||||
minijinja = { version = "2.2.0", features = ["json"] }
|
minijinja = { version = "2.2.0", features = ["json"] }
|
||||||
minijinja-contrib = { version = "2.0.2", features = ["pycompat"] }
|
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]
|
[profile.release]
|
||||||
incremental = true
|
incremental = true
|
||||||
|
10
backends/vllm/Cargo.toml
Normal file
10
backends/vllm/Cargo.toml
Normal file
@ -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"
|
6
backends/vllm/src/main.rs
Normal file
6
backends/vllm/src/main.rs
Normal file
@ -0,0 +1,6 @@
|
|||||||
|
use pyo3::prelude::*;
|
||||||
|
|
||||||
|
#[pyo3_asyncio::tokio::main(flavor = "multi_thread")]
|
||||||
|
async fn main() {
|
||||||
|
println!("Hello, world!");
|
||||||
|
}
|
Loading…
Reference in New Issue
Block a user