[workspace] members = [ "benchmark", "backends/v2", "backends/v3", "backends/grpc-metadata", "backends/trtllm", "launcher", "router" ] default-members = [ "benchmark", "backends/v2", "backends/v3", "backends/grpc-metadata", # "backends/trtllm", "launcher", "router" ] resolver = "2" [workspace.package] version = "2.3.1" edition = "2021" authors = ["Olivier Dehaene"] homepage = "https://github.com/huggingface/text-generation-inference" [workspace.dependencies] base64 = "0.22.0" tokenizers = { version = "0.20.0", features = ["http"] } hf-hub = { version = "0.3.1", features = ["tokio"] } 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"] } [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