Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
Large Language Model Text Generation Inference
33 Commits 179 Branches 50 Tags 605 MiB
Python 70.9%
Rust 22.2%
Cuda 4.7%
C++ 1%
Nix 0.4%
Other 0.7%
Go to file
Nick Hill 31d76e238d
fix(batching): Avoid theoretical hang in batcher loop (#5) 
- Avoid theoretical hang in batcher loop
- Avoid a couple of clones in the router generate method
- Keep attention mask tensors as integers
- Remove num_heads attribute

Co-authored-by: OlivierDehaene <Olivier.dehaene@gmail.com>
 		2022-12-05 10:10:59 +01:00
aml fix(server): Fix Transformers fork version 2022-11-08 17:42:38 +01:00
assets v0.1.0 2022-10-20 19:14:44 +02:00
k6 Add load testing 2022-10-11 10:36:51 +02:00
launcher feat(server): Improved doc 2022-11-07 12:53:56 +01:00
proto feat(server): Support AutoModelForSeq2SeqLM 2022-11-04 18:03:04 +01:00
router fix(batching): Avoid theoretical hang in batcher loop (#5) 2022-12-05 10:10:59 +01:00
server fix(batching): Avoid theoretical hang in batcher loop (#5) 2022-12-05 10:10:59 +01:00
.dockerignore fix(server): Fix Transformers fork version 2022-11-08 17:42:38 +01:00
.gitignore v0.1.0 2022-10-20 19:14:44 +02:00
Cargo.lock feat(server): Clarify CausalLMBatch concatenate method 2022-11-09 18:24:07 +01:00
Cargo.toml feat(rust): Update to 1.65 2022-11-14 13:59:56 +01:00
Dockerfile feat(rust): Update to 1.65 2022-11-14 13:59:56 +01:00
LICENSE Create LICENSE (#2) 2022-10-22 10:44:52 +02:00
Makefile feat(server): Support all AutoModelForCausalLM on a best effort basis 2022-10-28 19:24:00 +02:00
README.md feat(server): Support Galactica (#4) 2022-12-01 19:31:54 +01:00
rust-toolchain.toml feat(rust): Update to 1.65 2022-11-14 13:59:56 +01:00

README.md

Text Generation Inference

architecture

A Rust and gRPC server for text generation inference. Used in production at HuggingFace to power Bloom, BloomZ and MT0-XXL api-inference widgets.

Features

Officially supported models

Other models are supported on a best effort basis using:

AutoModelForCausalLM.from_pretrained(<model>, device_map="auto")

or

AutoModelForSeq2SeqLM.from_pretrained(<model>, device_map="auto")

Load Tests for BLOOM

See k6/load_test.js

avg min med max p(90) p(95) RPS
Original code 8.9s 1s 9.12s 16.69s 13.7s 14.26s 5.9
New batching logic 5.44s 959.53ms 5.28s 13.12s 7.78s 8.92s 9.08

Install

make install

Run

BLOOM 560-m

make run-bloom-560m

BLOOM

First you need to download the weights:

make download-bloom

make run-bloom # Requires 8xA100 80GB

You can also quantize the weights with bitsandbytes to reduce the VRAM requirement:

make run-bloom-quantize # Requires 8xA100 40GB

Test

curl 127.0.0.1:3000/generate \
    -v \
    -X POST \
    -d '{"inputs":"Testing API","parameters":{"max_new_tokens":9}}' \
    -H 'Content-Type: application/json'

Develop

make server-dev
make router-dev

TODO:

  • Add tests for the server/model logic
  • Backport custom CUDA kernels to Transformers