mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-06-03 05:02:12 +00:00
fc52ba61ab
Before this change, the generation input was sent to the backend as a single string, encoding images as Base64 and packing them in Markdown-style links. This change adds a new chunked input representation that separates text chunks from images chunks. Image chunks contain binary data (for smaller message sizes) and the image's MIME type. The stringly-typed inputs are still sent to support backends that do not support chunked inputs yet.
29 lines
559 B
TOML
29 lines
559 B
TOML
[workspace]
|
|
members = [
|
|
"benchmark",
|
|
"router",
|
|
"router/client",
|
|
"router/grpc-metadata",
|
|
"launcher"
|
|
]
|
|
resolver = "2"
|
|
|
|
[workspace.package]
|
|
version = "2.0.5-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"] }
|
|
|
|
[profile.release]
|
|
debug = 1
|
|
incremental = true
|
|
lto = "fat"
|
|
opt-level = 3
|
|
codegen-units = 1
|
|
panic = "abort"
|