mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-26 12:32:10 +00:00
55acb86f42
This WIP PR starts to add grammar support via outlines, currently this PR supports very simple regex grammars and does not optimize for precompiling or caching grammar fsm's. todo: - [X] add simple outlines guidance to `NextTokenChooser` - [X] update protos for grammar - [X] update generation params API - [X] constrain simple grammar - [ ] support parsing more complex grammar into fsm - [ ] support all outline support grammar types - [ ] explore optimizations to avoid recompiling grammars guided request ```bash curl -s 'http://localhost:3000/generate' \ --header 'Content-Type: application/json' \ --data-raw '{ "inputs": "make an email for david: \n", "parameters": { "max_new_tokens": 6, "grammar": "[\\w-]+@([\\w-]+\\.)+[\\w-]+" } }' | jq ``` response ```json { "generated_text": "david@example.com" } ``` unguided request ```bash curl -s 'http://localhost:3000/generate' \ --header 'Content-Type: application/json' \ --data '{ "inputs": "make an email for david: \n", "parameters": { "max_new_tokens": 6 } }' | jq ``` response ```json { "generated_text": " email = 'david" } ```
40 lines
1.0 KiB
TOML
40 lines
1.0 KiB
TOML
[tool.poetry]
|
|
name = "text-generation-server"
|
|
version = "1.4.0"
|
|
description = "Text Generation Inference Python gRPC Server"
|
|
authors = ["Olivier Dehaene <olivier@huggingface.co>"]
|
|
|
|
[tool.poetry.scripts]
|
|
text-generation-server = 'text_generation_server.cli:app'
|
|
|
|
[tool.poetry.dependencies]
|
|
python = ">=3.9,<3.13"
|
|
protobuf = "^3.20.3"
|
|
grpcio = "^1.51.1"
|
|
grpcio-status = "*"
|
|
grpcio-reflection = "*"
|
|
grpc-interceptor = "^0.15.0"
|
|
typer = "^0.6.1"
|
|
loguru = "^0.6.0"
|
|
opentelemetry-api = "^1.15.0"
|
|
opentelemetry-exporter-otlp = "^1.15.0"
|
|
opentelemetry-instrumentation-grpc = "^0.36b0"
|
|
hf-transfer = "^0.1.2"
|
|
sentencepiece = "^0.1.97"
|
|
peft = "^0.8.2"
|
|
optimum-habana = "1.10.4"
|
|
transformers = "4.37.2"
|
|
accelerate = "0.27.2"
|
|
outlines="^0.0.27"
|
|
|
|
[tool.poetry.group.dev.dependencies]
|
|
grpcio-tools = "*"
|
|
pytest = "^7.3.0"
|
|
|
|
[tool.pytest.ini_options]
|
|
markers = ["private: marks tests as requiring an admin hf token (deselect with '-m \"not private\"')"]
|
|
|
|
[build-system]
|
|
requires = ["poetry-core>=1.0.0"]
|
|
build-backend = "poetry.core.masonry.api"
|