hf_text-generation-inference/server
OlivierDehaene 7fbfbb0dc5
feat: Add token streaming using ServerSideEvents support (#36)
Add token streaming using ServerSideEvents (SSE).

The signature of the SSE events is: 

```rust
struct Details {
    finish_reason: String,
    generated_tokens: u32,
    seed: Option<u64>,
}

struct StreamResponse {
    token: Token,
    generated_text: Option<String>,
    details: Option<Details>,
}

struct ErrorResponse {
    error: String,
}
```
2023-01-31 11:49:43 +01:00
..
tests feat: Add token streaming using ServerSideEvents support (#36) 2023-01-31 11:49:43 +01:00
text_generation feat: Add token streaming using ServerSideEvents support (#36) 2023-01-31 11:49:43 +01:00
.gitignore feat(server): Support all AutoModelForCausalLM on a best effort basis 2022-10-28 19:24:00 +02:00
Makefile fix(dockerfile): fix docker build (#32) 2023-01-24 19:52:39 +01:00
README.md feat(server): Use safetensors 2022-10-22 20:00:15 +02:00
poetry.lock feat(launcher): Log server stdout (#19) 2023-01-05 12:01:23 +01:00
pyproject.toml feat(launcher): Log server stdout (#19) 2023-01-05 12:01:23 +01:00

README.md

BLOOM Inference Python gRPC Server

A Python gRPC server for BLOOM Inference

Install

make install

Run

make run-dev