49 lines
959 B
TOML
49 lines
959 B
TOML
[workspace]
|
|
members = [
|
|
"benchmark",
|
|
"backends/v3",
|
|
"backends/grpc-metadata",
|
|
"backends/trtllm",
|
|
"backends/client",
|
|
"launcher"
|
|
]
|
|
default-members = [
|
|
"benchmark",
|
|
"backends/v3",
|
|
"backends/grpc-metadata",
|
|
# "backends/trtllm",
|
|
"backends/client",
|
|
"launcher"
|
|
]
|
|
resolver = "2"
|
|
|
|
[workspace.package]
|
|
version = "2.2.1-dev0"
|
|
edition = "2021"
|
|
authors = ["Olivier Dehaene"]
|
|
homepage = "https://github.com/huggingface/text-generation-inference"
|
|
|
|
[workspace.dependencies]
|
|
base64 = "0.22.0"
|
|
tokenizers = { version = "0.19.1", features = ["http"] }
|
|
hf-hub = { version = "0.3.1", features = ["tokio"] }
|
|
metrics = { version = "0.23.0" }
|
|
metrics-exporter-prometheus = { version = "0.15.1", features = [] }
|
|
|
|
[profile.release]
|
|
incremental = true
|
|
|
|
[profile.release-binary]
|
|
inherits = "release"
|
|
debug = 1
|
|
incremental = true
|
|
panic = "abort"
|
|
|
|
[profile.release-opt]
|
|
inherits = "release"
|
|
debug = 0
|
|
incremental = false
|
|
lto = "fat"
|
|
opt-level = 3
|
|
codegen-units = 1
|