minor: Add basic editorconfig and pre-commit hooks to enforce style for whitespaces (#1926)

.editorconfig

+# https://editorconfig.org/
+
+root = true
+
+[*]
+charset = utf-8
+end_of_line = lf
+indent_style = space
+indent_size = 4
+trim_trailing_whitespace = true
+insert_final_newline = true
+
+[*.{json,yaml,yml}]
+indent_size = 2
+
+[*.md]
+indent_size = 2
+x-soft-wrap-text = true
+
+[*.rst]
+indent_size = 4
+x-soft-wrap-text = true
+
+[Makefile]
+indent_style = tab

.github/pull_request_template.md

@@ -12,4 +12,4 @@
 
 - [ ] Format your code according to the [Contributor Guide](https://github.com/sgl-project/sglang/blob/main/docs/contributor_guide.md).
 - [ ] Add unit tests as outlined in the [Contributor Guide](https://github.com/sgl-project/sglang/blob/main/docs/contributor_guide.md).
-- [ ] Update documentation as needed, including docstrings or example tutorials.
+- [ ] Update documentation as needed, including docstrings or example tutorials.
\ No newline at end of file

.github/workflows/close-inactive-issues.yml

@@ -20,10 +20,10 @@ jobs:
           github-token: ${{secrets.GITHUB_TOKEN}}
           script: |
             const sixtyDaysAgo = new Date(Date.now() - 60 * 24 * 60 * 60 * 1000);
-            
+
             const [owner, repo] = process.env.GITHUB_REPOSITORY.split('/');
             console.log(`Owner: ${owner}, Repo: ${repo}`);
-            
+
             async function fetchIssues(page = 1) {
               console.log(`Fetching issues for ${owner}/${repo}, page ${page}`);
               return await github.rest.issues.listForRepo({
@@ -36,23 +36,23 @@ jobs:
                 page: page
               });
             }
-            
+
             async function processIssues() {
               console.log('Starting to process issues');
               console.log(`Repository: ${owner}/${repo}`);
-              
+
               let page = 1;
               let hasMoreIssues = true;
               while (hasMoreIssues) {
                 try {
                   const issues = await fetchIssues(page);
                   console.log(`Fetched ${issues.data.length} issues on page ${page}`);
-                  
+
                   if (issues.data.length === 0) {
                     hasMoreIssues = false;
                     break;
                   }
-                  
+
                   for (const issue of issues.data) {
                     if (new Date(issue.updated_at) < sixtyDaysAgo) {
                       try {
@@ -87,5 +87,5 @@ jobs:
               }
               console.log('Finished processing issues');
             }
-            
+
             await processIssues();

.github/workflows/execute-notebook.yml

@@ -18,7 +18,7 @@ concurrency:
   group: execute-notebook-${{ github.ref }}
   cancel-in-progress: true
 
-  
+
 jobs:
   run-all-notebooks:
     runs-on: 1-gpu-runner
@@ -45,4 +45,4 @@ jobs:
         run: |
           cd docs
           make clean
-          make compile
+          make compile
\ No newline at end of file

.github/workflows/pr-test-rust.yml

@@ -36,4 +36,4 @@ jobs:
         run: |
           source "$HOME/.cargo/env"
           cd rust/
-          cargo test
+          cargo test
\ No newline at end of file

.github/workflows/pr-test.yml

@@ -237,7 +237,7 @@ jobs:
         run: |
           cd test/srt
           python3 test_moe_eval_accuracy_large.py
-      
+
       - name: Evaluate MLA Accuracy (TP=2)
         timeout-minutes: 10
         run: |

.github/workflows/release-docs.yml

@@ -47,7 +47,7 @@ jobs:
 
           make html
           cd _build/html
-          
+
           git clone https://$GITHUB_TOKEN@github.com/sgl-project/sgl-project.github.io.git ../sgl-project.github.io --depth 1
           rm -rf  ../sgl-project.github.io/*
           cp -r * ../sgl-project.github.io

.gitignore

@@ -185,4 +185,4 @@ tmp*.txt
 work_dirs/
 *.csv
 
-!logo.png
+!logo.png
\ No newline at end of file

.isort.cfg

 [settings]
 profile=black
-known_first_party=sglang
+known_first_party=sglang
\ No newline at end of file

.pre-commit-config.yaml

 default_language_version:
     python: python3.9
 
+default_stages: [pre-commit, pre-push, manual]
+
 repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+      - id: check-symlinks
+      - id: destroyed-symlinks
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-yaml
+        args: [--allow-multiple-documents]
+      - id: check-toml
+      - id: check-ast
+      - id: check-added-large-files
+      - id: check-merge-conflict
+      - id: check-executables-have-shebangs
+      - id: check-shebang-scripts-are-executable
+      - id: detect-private-key
+      - id: debug-statements
+      - id: no-commit-to-branch
   - repo: https://github.com/PyCQA/isort
     rev: 5.13.2
     hooks:
@@ -13,8 +33,3 @@ repos:
         additional_dependencies: ['.[jupyter]']
         types: [python, jupyter]
         types_or: [python, jupyter]
-
-  - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v5.0.0
-    hooks:
-      - id: no-commit-to-branch
\ No newline at end of file

3rdparty/amd/profiling/PROFILING.md

@@ -6,5 +6,3 @@ Two primary methods are covered:
 
 
 - [Torch Profiler](https://pytorch.org/tutorials/recipes/recipes/profiler_recipe.html)
-
-

3rdparty/amd/tuning/TUNING.md

@@ -29,18 +29,18 @@ def _triton_kernel_funtion():
     ...
 ```
 ## 2. Torch Tunable Operations
-**TunableOp** is a feature in PyTorch that allows for the definition and optimization of custom kernels with tunable parameters. This feature is particularly useful for enhancing the performance of kernels by experimenting with different configurations. 
+**TunableOp** is a feature in PyTorch that allows for the definition and optimization of custom kernels with tunable parameters. This feature is particularly useful for enhancing the performance of kernels by experimenting with different configurations.
 
 ### Key Environment Variables:
-1. **PYTORCH_TUNABLEOP_ENABLED**: 
+1. **PYTORCH_TUNABLEOP_ENABLED**:
    - Default: `0`
    - Set to `1` to enable TunableOp.
 
-2. **PYTORCH_TUNABLEOP_TUNING**: 
+2. **PYTORCH_TUNABLEOP_TUNING**:
    - Default: `1`
    - Set to `0` to disable tuning. If a tuned entry is not found, it will run the tuning step and record the entry when PYTORCH_TUNABLEOP_ENABLED is enabled.
 
-3. **PYTORCH_TUNABLEOP_VERBOSE**: 
+3. **PYTORCH_TUNABLEOP_VERBOSE**:
    - Default: `0`
    - Set to `1` to enable verbose output for TunableOp.
 
@@ -66,20 +66,20 @@ The following are suggestions for optimizing matrix multiplication (GEMM) and co
 To tune Triton kernels with GEMM and convolution ops (conv), use the `torch.compile` function with the max-autotune mode. This benchmarks a predefined list of Triton configurations and selects the fastest one for each shape.
 
 ### Key Configurations:
-1. **Max Autotune**: 
+1. **Max Autotune**:
    - Set `torch._inductor.config.max_autotune = True` or `TORCHINDUCTOR_MAX_AUTOTUNE=1`.
 
 2. **Fine-Grained Control**:
    - Enable GEMM tuning: `torch._inductor.config.max_autotune_gemm = True`.
    - Enable tuning for pointwise/reduction ops: `torch._inductor.config.max_autotune.pointwise = True`.
 
-3. **Backend Selection**: 
+3. **Backend Selection**:
    - Use `torch._inductor.max_autotune_gemm_backends` to limit backends to TRITON for better performance.
 
-4. **Freezing for Inference**: 
+4. **Freezing for Inference**:
    - Use `torch._inductor.config.freezing=True` to enable constant folding optimizations.
 
-5. **Debugging**: 
+5. **Debugging**:
    - Set `TORCH_COMPILE_DEBUG=1` to extract Triton kernels generated by Inductor.
 
 ### Example Code Block:
@@ -98,4 +98,4 @@ TORCHINDUCTOR_FREEZING=1 your_script.sh
 
 For more detailed information on tuning SGLang performance with AMD GPUs, please refer to the following link:
 
-[ROCm Documentation: Triton Kernel Performance Optimization](https://rocm.docs.amd.com/en/latest/how-to/tuning-guides/mi300x/workload.html#triton-kernel-performance-optimization)
+[ROCm Documentation: Triton Kernel Performance Optimization](https://rocm.docs.amd.com/en/latest/how-to/tuning-guides/mi300x/workload.html#triton-kernel-performance-optimization)
\ No newline at end of file

benchmark/blog_v0_2/405b_sglang.sh

@@ -21,4 +21,4 @@ python3 -m sglang.bench_serving --backend sglang --dataset-name random --num-pro
 python3 -m sglang.bench_serving --backend sglang --dataset-name random --num-prompt 600 --request-rate 2 --random-input 1024 --random-output 1024 > sglang_log32
 python3 -m sglang.bench_serving --backend sglang --dataset-name random --num-prompt 1200 --request-rate 4 --random-input 1024 --random-output 1024 > sglang_log33
 python3 -m sglang.bench_serving --backend sglang --dataset-name random --num-prompt 2400 --request-rate 8 --random-input 1024 --random-output 1024 > sglang_log34
-python3 -m sglang.bench_serving --backend sglang --dataset-name random --num-prompt 3200 --request-rate 16 --random-input 1024 --random-output 1024 > sglang_log35
+python3 -m sglang.bench_serving --backend sglang --dataset-name random --num-prompt 3200 --request-rate 16 --random-input 1024 --random-output 1024 > sglang_log35
\ No newline at end of file

benchmark/blog_v0_2/405b_vllm.sh

@@ -21,4 +21,4 @@ python3 ../../python/sglang/bench_serving.py --backend vllm --dataset-name rando
 python3 ../../python/sglang/bench_serving.py --backend vllm --dataset-name random --num-prompt 600 --request-rate 2 --random-input 1024 --random-output 1024 > vllm_log32
 python3 ../../python/sglang/bench_serving.py --backend vllm --dataset-name random --num-prompt 1200 --request-rate 4 --random-input 1024 --random-output 1024 > vllm_log33
 python3 ../../python/sglang/bench_serving.py --backend vllm --dataset-name random --num-prompt 2400 --request-rate 8 --random-input 1024 --random-output 1024 > vllm_log34
-python3 ../../python/sglang/bench_serving.py --backend vllm --dataset-name random --num-prompt 3200 --request-rate 16 --random-input 1024 --random-output 1024 > vllm_log35
+python3 ../../python/sglang/bench_serving.py --backend vllm --dataset-name random --num-prompt 3200 --request-rate 16 --random-input 1024 --random-output 1024 > vllm_log35
\ No newline at end of file

benchmark/generative_agents/agent_functions.py

@@ -30,22 +30,22 @@ def poignancy_event_prompt(persona_name, persona_iss, event):
 @sgl.function
 def generate_event_triple(s, persona_name, action):
     s += """Task: Turn the input into (subject, predicate, object).
-Input: Sam Johnson is eating breakfast. 
-Output: (Dolores Murphy, eat, breakfast) 
---- 
+Input: Sam Johnson is eating breakfast.
+Output: (Dolores Murphy, eat, breakfast)
+---
 Input: Joon Park is brewing coffee.
 Output: (Joon Park, brew, coffee)
 ---
-Input: Jane Cook is sleeping. 
+Input: Jane Cook is sleeping.
 Output: (Jane Cook, is, sleep)
 ---
-Input: Michael Bernstein is writing email on a computer. 
+Input: Michael Bernstein is writing email on a computer.
 Output: (Michael Bernstein, write, email)
 ---
-Input: Percy Liang is teaching students in a classroom. 
+Input: Percy Liang is teaching students in a classroom.
 Output: (Percy Liang, teach, students)
 ---
-Input: Merrie Morris is running on a treadmill. 
+Input: Merrie Morris is running on a treadmill.
 Output: (Merrie Morris, run, treadmill)
 ---"""
     s += persona_name + "is" + action + ".\n"
@@ -56,22 +56,22 @@ Output: (Merrie Morris, run, treadmill)
 def generate_event_triple_prompt(persona_name, action):
     s = ""
     s += """Task: Turn the input into (subject, predicate, object).
-Input: Sam Johnson is eating breakfast. 
-Output: (Dolores Murphy, eat, breakfast) 
---- 
+Input: Sam Johnson is eating breakfast.
+Output: (Dolores Murphy, eat, breakfast)
+---
 Input: Joon Park is brewing coffee.
 Output: (Joon Park, brew, coffee)
 ---
-Input: Jane Cook is sleeping. 
+Input: Jane Cook is sleeping.
 Output: (Jane Cook, is, sleep)
 ---
-Input: Michael Bernstein is writing email on a computer. 
+Input: Michael Bernstein is writing email on a computer.
 Output: (Michael Bernstein, write, email)
 ---
-Input: Percy Liang is teaching students in a classroom. 
+Input: Percy Liang is teaching students in a classroom.
 Output: (Percy Liang, teach, students)
 ---
-Input: Merrie Morris is running on a treadmill. 
+Input: Merrie Morris is running on a treadmill.
 Output: (Merrie Morris, run, treadmill)
 ---"""
     s += persona_name + "is" + action + ".\n"
@@ -107,9 +107,9 @@ def action_location_sector(
     current_action,
     next_action,
 ):
-    s += """Task -- choose an appropriate area  from the area options for a task at hand. 
+    s += """Task -- choose an appropriate area  from the area options for a task at hand.
 Sam Kim lives in {Sam Kim's house} that has Sam Kim's room, bathroom, kitchen.
-Sam Kim is currently in {Sam Kim's house} that has Sam Kim's room, bathroom, kitchen. 
+Sam Kim is currently in {Sam Kim's house} that has Sam Kim's room, bathroom, kitchen.
 Area options: {Sam Kim's house, The Rose and Crown Pub, Hobbs Cafe, Oak Hill College, Johnson Park, Harvey Oak Supply Store, The Willows Market and Pharmacy}.
 * Stay in the current area if the activity can be done there. Only go out if the activity needs to take place in another place.
 * Must be one of the "Area options," verbatim.
@@ -117,7 +117,7 @@ For taking a walk, Sam Kim should go to the following area: {Johnson Park}
 ---
 Jane Anderson lives in {Oak Hill College Student Dormatory} that has Jane Anderson's room.
 Jane Anderson is currently in {Oak Hill College} that has a classroom, library
-Area options: {Oak Hill College Student Dormatory, The Rose and Crown Pub, Hobbs Cafe, Oak Hill College, Johnson Park, Harvey Oak Supply Store, The Willows Market and Pharmacy}. 
+Area options: {Oak Hill College Student Dormatory, The Rose and Crown Pub, Hobbs Cafe, Oak Hill College, Johnson Park, Harvey Oak Supply Store, The Willows Market and Pharmacy}.
 * Stay in the current area if the activity can be done there. Only go out if the activity needs to take place in another place.
 * Must be one of the "Area options," verbatim.
 For eating dinner, Jane Anderson should go to the following area: {Hobbs Cafe}
@@ -167,9 +167,9 @@ def action_location_sector_prompt(
     next_action,
 ):
     s = ""
-    s += """Task -- choose an appropriate area  from the area options for a task at hand. 
+    s += """Task -- choose an appropriate area  from the area options for a task at hand.
 Sam Kim lives in {Sam Kim's house} that has Sam Kim's room, bathroom, kitchen.
-Sam Kim is currently in {Sam Kim's house} that has Sam Kim's room, bathroom, kitchen. 
+Sam Kim is currently in {Sam Kim's house} that has Sam Kim's room, bathroom, kitchen.
 Area options: {Sam Kim's house, The Rose and Crown Pub, Hobbs Cafe, Oak Hill College, Johnson Park, Harvey Oak Supply Store, The Willows Market and Pharmacy}.
 * Stay in the current area if the activity can be done there. Only go out if the activity needs to take place in another place.
 * Must be one of the "Area options," verbatim.
@@ -177,7 +177,7 @@ For taking a walk, Sam Kim should go to the following area: {Johnson Park}
 ---
 Jane Anderson lives in {Oak Hill College Student Dormatory} that has Jane Anderson's room.
 Jane Anderson is currently in {Oak Hill College} that has a classroom, library
-Area options: {Oak Hill College Student Dormatory, The Rose and Crown Pub, Hobbs Cafe, Oak Hill College, Johnson Park, Harvey Oak Supply Store, The Willows Market and Pharmacy}. 
+Area options: {Oak Hill College Student Dormatory, The Rose and Crown Pub, Hobbs Cafe, Oak Hill College, Johnson Park, Harvey Oak Supply Store, The Willows Market and Pharmacy}.
 * Stay in the current area if the activity can be done there. Only go out if the activity needs to take place in another place.
 * Must be one of the "Area options," verbatim.
 For eating dinner, Jane Anderson should go to the following area: {Hobbs Cafe}
@@ -226,7 +226,7 @@ Stay in the current area if the activity can be done there. Never go into other
 For cooking, Jane Anderson should go to the following area in Jane Anderson's house:
 Answer: {kitchen}
 ---
-Tom Watson is in common room in Tom Watson's apartment. 
+Tom Watson is in common room in Tom Watson's apartment.
 Tom Watson is going to Hobbs Cafe that has the following areas: {cafe}
 Stay in the current area if the activity can be done there. Never go into other people's rooms unless necessary.
 For getting coffee, Tom Watson should go to the following area in Hobbs Cafe:
@@ -240,7 +240,7 @@ Answer: {cafe}
         + target_sector_areas
         + "}\n"
     )
-    s += """* Stay in the current area if the activity can be done there. 
+    s += """* Stay in the current area if the activity can be done there.
 * NEVER go into other people's rooms unless necessary."""
     s += (
         persona_name
@@ -268,7 +268,7 @@ Stay in the current area if the activity can be done there. Never go into other
 For cooking, Jane Anderson should go to the following area in Jane Anderson's house:
 Answer: {kitchen}
 ---
-Tom Watson is in common room in Tom Watson's apartment. 
+Tom Watson is in common room in Tom Watson's apartment.
 Tom Watson is going to Hobbs Cafe that has the following areas: {cafe}
 Stay in the current area if the activity can be done there. Never go into other people's rooms unless necessary.
 For getting coffee, Tom Watson should go to the following area in Hobbs Cafe:
@@ -282,7 +282,7 @@ Answer: {cafe}
         + target_sector_areas
         + "}\n"
     )
-    s += """* Stay in the current area if the activity can be done there. 
+    s += """* Stay in the current area if the activity can be done there.
 * NEVER go into other people's rooms unless necessary."""
     s += (
         persona_name

benchmark/json_decode_regex/README.md

@@ -20,7 +20,7 @@ outlines                  0.0.22
 Run Llama-7B
 
 ```
-python3 -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --port 30000 
+python3 -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --port 30000
 ```
 
 Run Mixtral-8x7B

benchmark/json_jump_forward/README.md

@@ -23,7 +23,7 @@ python3 build_dataset.py
 Run Llama-7B
 
 ```bash
-python3 -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --port 30000 
+python3 -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --port 30000
 ```
 
 Benchmark Character Generation

benchmark/json_jump_forward/dataset.txt

@@ -47,4 +47,4 @@ Quirinus Quirrell
 Nearly Headless Nick
 Aunt Marge
 Griphook
-Ludo Bagman
+Ludo Bagman
\ No newline at end of file

benchmark/llava_bench/README.md

@@ -4,7 +4,7 @@
 python3 download_images.py
 ```
 
-image benchmark source: https://huggingface.co/datasets/liuhaotian/llava-bench-in-the-wild 
+image benchmark source: https://huggingface.co/datasets/liuhaotian/llava-bench-in-the-wild
 
 ### Other Dependency
 ```