mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-05-01 15:02:09 +00:00
cef0553d59
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" } ```
64 lines
1.7 KiB
TOML
64 lines
1.7 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 = "^4.21.7"
|
|
grpcio = "^1.51.1"
|
|
grpcio-status = "^1.51.1"
|
|
grpcio-reflection = "^1.51.1"
|
|
grpc-interceptor = "^0.15.0"
|
|
typer = "^0.6.1"
|
|
accelerate = { version = "^0.25.0", optional = true }
|
|
bitsandbytes = { version = "^0.41.1", optional = true }
|
|
safetensors = "^0.3.2"
|
|
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"
|
|
tokenizers = "^0.15.0"
|
|
huggingface-hub = "^0.19.3"
|
|
transformers = "^4.37.1"
|
|
einops = "^0.6.1"
|
|
texttable = { version = "^1.6.7", optional = true }
|
|
datasets = { version = "^2.14.0", optional = true }
|
|
peft = { version = "^0.8.2", optional = true }
|
|
torch = { version = "^2.1.1", optional = true }
|
|
scipy = "^1.11.1"
|
|
pillow = "^10.0.0"
|
|
outlines="^0.0.27"
|
|
|
|
[tool.poetry.extras]
|
|
torch = ["torch"]
|
|
accelerate = ["accelerate"]
|
|
bnb = ["bitsandbytes"]
|
|
peft = ["peft"]
|
|
quantize = ["texttable", "datasets", "accelerate"]
|
|
|
|
[tool.poetry.group.dev.dependencies]
|
|
grpcio-tools = "^1.51.1"
|
|
pytest = "^7.3.0"
|
|
|
|
|
|
[[tool.poetry.source]]
|
|
name = "pytorch-gpu-src"
|
|
url = "https://download.pytorch.org/whl/cu121"
|
|
priority = "explicit"
|
|
|
|
[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"
|