vllm-coldstart-operator/Cargo.toml at main · MicheleCampi/vllm-coldstart-operator · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
[package]
name = "vllm-coldstart-operator"
version = "0.3.0"
edition = "2021"
rust-version = "1.83"
license = "Apache-2.0"
description = "A Kubernetes operator that manages vLLM inference replicas with cold-start as a first-class signal"
repository = "https://github.com/MicheleCampi/vllm-coldstart-operator"

[dependencies]
kube = { version = "2", features = ["runtime", "derive", "client"] }
k8s-openapi = { version = "0.26", features = ["v1_34"] }
tokio = { version = "1", features = ["macros", "rt-multi-thread"] }
serde = { version = "1", features = ["derive"] }
serde_json = "1"
schemars = "1"
thiserror = "2"
tracing = "0.1"
tracing-subscriber = { version = "0.3", features = ["env-filter"] }
futures = "0.3"
anyhow = "1.0.102"
serde_yaml = "0.9.34"
prometheus-client = "0.24"
axum = "0.8"
reqwest = { version = "0.13.3", default-features = false, features = ["rustls"] }
async-trait = "0.1.91"
rustls = { version = "0.23.42", default-features = false, features = ["ring"] }
nvml-wrapper = { version = "0.12", optional = true }

[dev-dependencies]
proptest = "1.11"

[features]
default = []
gpu-nvidia = ["dep:nvml-wrapper"]