chore: add pre-commit (#1569)

Author: OlivierDehaene

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -5,14 +5,14 @@ body:
     id: system-info
     attributes:
       label: System Info
-      description: | 
+      description: |
         Please share your system info with us (`text-generation-launcher --env` if installed locally).
-        The full command line used that causes issues: 
+        The full command line used that causes issues:
         OS version:
         Rust version (if self-compiling, `cargo version`):
         Model being used (`curl 127.0.0.1:8080/info | jq`):
           If local model please explicit the kind of model and/or equivalents.
-        Hardware used (GPUs, how many, on which cloud) (`nvidia-smi`): 
+        Hardware used (GPUs, how many, on which cloud) (`nvidia-smi`):
         Deployment specificities (Kubernetes, EKS, AKS, any particular deployments):
         The current version being used:
 
@@ -52,11 +52,11 @@ body:
 
       placeholder: |
         Steps to reproduce the behavior:
-          
+
           1.
           2.
           3.
-          
+
 
   - type: textarea
     id: expected-behavior

.github/ISSUE_TEMPLATE/feature-request.yml

@@ -19,7 +19,7 @@ body:
       label: Motivation
       description: |
         Please outline the motivation for the proposal. Is your feature request related to a problem? e.g., I'm always frustrated when [...]. If this is related to another GitHub issue, please link here too.
-        
+
 
   - type: textarea
     id: contribution

.github/workflows/autodocs.yml

@@ -6,15 +6,15 @@ on:
 jobs:
   update_docs:
     runs-on: ubuntu-latest
-    
+
     steps:
     - name: Checkout code
       uses: actions/checkout@v2
-    
+
     - name: Install Launcher
       id: install-launcher
       run: cargo install --git https://github.com/${{ github.repository }} --branch ${{ github.head_ref }} text-generation-launcher
-    
+
     - name: Check launcher Docs are up-to-date
       run: |
         echo text-generation-launcher --help

.github/workflows/build_pr_documentation.yml

@@ -16,4 +16,4 @@ jobs:
       commit_sha: ${{ github.event.pull_request.head.sha }}
       pr_number: ${{ github.event.number }}
       package: text-generation-inference
-      additional_args: --not_python_module 
+      additional_args: --not_python_module

.github/workflows/tests.yaml

@@ -71,12 +71,11 @@ jobs:
           pip install pytest
           export HUGGING_FACE_HUB_TOKEN=${{ secrets.HUGGING_FACE_HUB_TOKEN }}
           pytest -s -vv server/tests
-      - name: Run Rust fmt
+      - name: Pre-commit checks
         run: |
-          cargo fmt --check
-      - name: Run Rust clippy
-        run: |
-          cargo clippy
+          pip install pre-commit
+          pre-commit install
+          pre-commit run --all-files
       - name: Run Rust tests
         run: |
           cargo test

.github/workflows/upload_pr_documentation.yml

@@ -13,4 +13,4 @@ jobs:
       package_name: text-generation-inference
     secrets:
       hf_token: ${{ secrets.HF_DOC_BUILD_PUSH }}
-      comment_bot_token: ${{ secrets.COMMENT_BOT_TOKEN }}
+      comment_bot_token: ${{ secrets.COMMENT_BOT_TOKEN }}

.gitignore

@@ -11,4 +11,3 @@ server/exllama_kernels/exllama_kernels/hip_func/
 *_hip.cuh
 server/exllama_kernels/exllama_kernels/hip_buffers.cuh
 server/exllama_kernels/exllama_kernels/exllama_ext_hip.cpp
-

.pre-commit-config.yaml

@@ -0,0 +1,18 @@
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.5.0
+    hooks:
+    -   id: check-yaml
+    -   id: end-of-file-fixer
+    -   id: trailing-whitespace
+        exclude: docs/source/basic_tutorials/launcher.md
+-   repo: https://github.com/psf/black
+    rev: 24.2.0
+    hooks:
+    -   id: black
+-   repo: https://github.com/doublify/pre-commit-rust
+    rev: v1.0
+    hooks:
+    -   id: fmt
+    -   id: cargo-check
+    -   id: clippy

README.md

@@ -1,5 +1,5 @@
 <div align="center">
-  
+
 <a href="https://www.youtube.com/watch?v=jlMAX2Oaht0">
   <img width=560 width=315 alt="Making TGI deployment optimal" src="https://huggingface.co/datasets/Narsil/tgi_assets/resolve/main/thumbnail.png">
 </a>
@@ -228,7 +228,7 @@ text-generation-launcher --model-id mistralai/Mistral-7B-Instruct-v0.2
 You can also quantize the weights with bitsandbytes to reduce the VRAM requirement:
 
 ```shell
-text-generation-launcher --model-id mistralai/Mistral-7B-Instruct-v0.2 --quantize 
+text-generation-launcher --model-id mistralai/Mistral-7B-Instruct-v0.2 --quantize
 ```
 
 4bit quantization is available using the [NF4 and FP4 data types from bitsandbytes](https://arxiv.org/pdf/2305.14314.pdf). It can be enabled by providing `--quantize bitsandbytes-nf4` or `--quantize bitsandbytes-fp4` as a command line argument to `text-generation-launcher`.

benchmark/Cargo.toml

@@ -29,4 +29,3 @@ tui = {package = "ratatui", version = "0.23", default-features = false, features
 tracing = "0.1.37"
 tracing-subscriber = { version = "0.3.17", features = ["json", "env-filter"] }
 hf-hub = "0.3.1"
-