v0.8.0
This commit is contained in:
parent
b8b950b37c
commit
081b926584
|
@ -2557,7 +2557,7 @@ dependencies = [
|
|||
|
||||
[[package]]
|
||||
name = "text-generation-benchmark"
|
||||
version = "0.7.0"
|
||||
version = "0.8.0"
|
||||
dependencies = [
|
||||
"average",
|
||||
"clap",
|
||||
|
@ -2577,7 +2577,7 @@ dependencies = [
|
|||
|
||||
[[package]]
|
||||
name = "text-generation-client"
|
||||
version = "0.7.0"
|
||||
version = "0.8.0"
|
||||
dependencies = [
|
||||
"futures",
|
||||
"grpc-metadata",
|
||||
|
@ -2593,7 +2593,7 @@ dependencies = [
|
|||
|
||||
[[package]]
|
||||
name = "text-generation-launcher"
|
||||
version = "0.7.0"
|
||||
version = "0.8.0"
|
||||
dependencies = [
|
||||
"clap",
|
||||
"ctrlc",
|
||||
|
@ -2609,7 +2609,7 @@ dependencies = [
|
|||
|
||||
[[package]]
|
||||
name = "text-generation-router"
|
||||
version = "0.7.0"
|
||||
version = "0.8.0"
|
||||
dependencies = [
|
||||
"async-stream",
|
||||
"axum",
|
||||
|
|
|
@ -8,7 +8,7 @@ members = [
|
|||
]
|
||||
|
||||
[workspace.package]
|
||||
version = "0.7.0"
|
||||
version = "0.8.0"
|
||||
edition = "2021"
|
||||
authors = ["Olivier Dehaene"]
|
||||
homepage = "https://github.com/huggingface/text-generation-inference"
|
||||
|
|
|
@ -42,7 +42,7 @@ to power LLMs api-inference widgets.
|
|||
- Serve the most popular Large Language Models with a simple launcher
|
||||
- Tensor Parallelism for faster inference on multiple GPUs
|
||||
- Token streaming using Server-Sent Events (SSE)
|
||||
- [Continous batching of incoming requests](https://github.com/huggingface/text-generation-inference/tree/main/router) for increased total throughput
|
||||
- [Continuous batching of incoming requests](https://github.com/huggingface/text-generation-inference/tree/main/router) for increased total throughput
|
||||
- Optimized transformers code for inference using [flash-attention](https://github.com/HazyResearch/flash-attention) on the most popular architectures
|
||||
- Quantization with [bitsandbytes](https://github.com/TimDettmers/bitsandbytes)
|
||||
- [Safetensors](https://github.com/huggingface/safetensors) weight loading
|
||||
|
@ -61,6 +61,9 @@ to power LLMs api-inference widgets.
|
|||
- [Llama](https://github.com/facebookresearch/llama)
|
||||
- [OPT](https://huggingface.co/facebook/opt-66b)
|
||||
- [SantaCoder](https://huggingface.co/bigcode/santacoder)
|
||||
- [Starcoder](https://huggingface.co/bigcode/starcoder)
|
||||
- [Falcon 7B](https://huggingface.co/tiiuae/falcon-7b)
|
||||
- [Falcon 40B](https://huggingface.co/tiiuae/falcon-40b)
|
||||
|
||||
Other architectures are supported on a best effort basis using:
|
||||
|
||||
|
@ -81,7 +84,7 @@ model=bigscience/bloom-560m
|
|||
num_shard=2
|
||||
volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
|
||||
|
||||
docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:0.7 --model-id $model --num-shard $num_shard
|
||||
docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:0.8 --model-id $model --num-shard $num_shard
|
||||
```
|
||||
**Note:** To use GPUs, you need to install the [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html). We also recommend using NVIDIA drivers with CUDA version 11.8 or higher.
|
||||
|
||||
|
|
|
@ -10,7 +10,7 @@
|
|||
"name": "Apache 2.0",
|
||||
"url": "https://www.apache.org/licenses/LICENSE-2.0"
|
||||
},
|
||||
"version": "0.7.0"
|
||||
"version": "0.8.0"
|
||||
},
|
||||
"paths": {
|
||||
"/": {
|
||||
|
|
|
@ -1,6 +1,6 @@
|
|||
[tool.poetry]
|
||||
name = "text-generation-server"
|
||||
version = "0.7.0"
|
||||
version = "0.8.0"
|
||||
description = "Text Generation Inference Python gRPC Server"
|
||||
authors = ["Olivier Dehaene <olivier@huggingface.co>"]
|
||||
|
||||
|
|
|
@ -1,9 +0,0 @@
|
|||
[
|
||||
"bigcode/santacoder",
|
||||
"bigscience/bloom",
|
||||
"bigscience/bloomz",
|
||||
"EleutherAI/gpt-neox-20b",
|
||||
"google/flan-ul2",
|
||||
"google/flan-t5-xxl",
|
||||
"OpenAssistant/oasst-sft-1-pythia-12b"
|
||||
]
|
Loading…
Reference in New Issue