merge python reqs and fix doc (#81)

Signed-off-by: Rashid Kaleem <230885705+arekay-nv@users.noreply.github.com>

Author: arekay-nv

docs/CLI_QUICK_REFERENCE.md

@@ -24,12 +24,11 @@ inference-endpoint benchmark offline \
   --endpoint URL \
   --model Qwen/Qwen3-8B \
   --dataset tests/datasets/dummy_1k.pkl \
-  --report-path my_benchmark_report
+  --report-dir my_benchmark_report
 
 # YAML-based (YAML mode - no CLI overrides)
 inference-endpoint benchmark from-config \
-  --config test.yaml \
-  --output results.json
+  --config test.yaml
 ```
 
 **Default Test Dataset:** Use `tests/datasets/dummy_1k.pkl` (1000 samples, ~133 KB) for local testing.
@@ -69,8 +68,7 @@ inference-endpoint info
 - `--model NAME` - Model name (required for CLI mode, e.g., Qwen/Qwen3-8B)
 - `--dataset, -d PATH` - Dataset file (required for CLI mode)
 - `--config, -c PATH` - YAML config file (required for from-config mode)
-- `--output, -o PATH` - Save results to JSON
-- `--report-path PATH` - Save detailed benchmark report with metrics
+- `--report-dir PATH` - Save detailed benchmark report with metrics
 - `--verbose, -v` - Increase verbosity (-vv for debug)
 
 ## Benchmark Options (CLI Mode Only)
@@ -96,9 +94,6 @@ inference-endpoint info
 
 - `pkl` - Pickle format (default)
 - `hf` - HuggingFace datasets
-
-**Coming Soon:**
-
 - `jsonl` - JSON Lines format
 
 ## Test Modes
@@ -193,7 +188,7 @@ inference-endpoint init --template submission
 # 3. Run (YAML mode - no CLI overrides)
 inference-endpoint benchmark from-config \
   --config submission_template.yaml \
-  --output official_results.json
+  --report-dir official_results
 ```
 
 ### Validate First

docs/DEVELOPMENT.md

@@ -24,7 +24,7 @@ source venv/bin/activate  # On Windows: venv\Scripts\activate
 
 # 3. Install development dependencies
 pip install -e .
-pip install -r requirements/dev.txt
+pip install -r requirements/base.txt
 
 # 4. Install pre-commit hooks
 pre-commit install
@@ -287,15 +287,14 @@ python -m pdb -m pytest test_file.py
 
 ### Adding Dependencies
 
-1. **Base Dependencies** (`requirements/base.txt`): Required for package to function
-2. **Development Dependencies** (`requirements/dev.txt`): Development tools, linters, and pre-commit hooks
-3. **Test Dependencies** (`requirements/test.txt`): Testing framework and utilities (pytest, pytest-asyncio, etc.)
+1. **Base Dependencies** (`requirements/base.txt`): Required for package to function, development tools, linters, and pre-commit hooks
+2. **Test Dependencies** (`requirements/test.txt`): Testing framework and utilities (pytest, pytest-asyncio, etc.)
 
 ### Updating Dependencies
 
 ```bash
 # Update all dependencies
-pip install --upgrade -r requirements/dev.txt
+pip install --upgrade -r requirements/base.txt
 
 # Check for outdated packages
 pip list --outdated

docs/GITHUB_SETUP.md

@@ -14,10 +14,6 @@ Runs pre-commit hooks (ruff, formatters) on every PR and push.
 
 Automatically requests code reviews on new PRs.
 
-### Branch Validator (`.github/workflows/branch-validator.yml`)
-
-Enforces branch naming: `feature/*`, `bugfix/*`, `hotfix/*`, `docs/*`, `test/*`, `refactor/*`, `chore/*`, `release/*`.
-
 ### Test Workflow (`.github/workflows/test.yml`)
 
 Runs pytest test suite and generates coverage reports.

examples/README.md

@@ -16,6 +16,14 @@ Benchmarking a real-world model served via open-source serving systems such as [
 
 Compare `inference-endpoint` with [vLLM's](https://github.com/vllm-project/vllm) benchmarking tool.
 
+### [04_GPTOSS120B_Example](04_GPTOSS120B_Example/)
+
+Sample yaml configuration to benchmark `openai/gpt-oss-120b`.
+
+### [05_Llama3.1-8B_Example](05_Llama3.1-8B_Example/)
+
+Sample yaml configuration to benchmark `meta-llama/Llama-3.1-8B-Instruct`.
+
 ## Getting Help
 
 - For general usage: See main [README](../README.md)

requirements/base.txt

@@ -1,5 +1,9 @@
-# Base dependencies for the MLPerf Inference Endpoint Benchmarking System
-# These are the minimal dependencies required for the package to function
+# Dependencies for the MLPerf Inference Endpoint Benchmarking System
+# Install with: pip install -r requirements/base.txt
+
+# ============================================================================
+# Core Runtime Dependencies
+# ============================================================================
 
 # Core Python dependencies
 typing-extensions>=4.0.0
@@ -8,18 +12,19 @@ typing-extensions>=4.0.0
 psutil==6.1.1
 
 # Note: asyncio is part of Python 3.11+ standard library
-# Additional dependencies will be added as components are implemented
+# Async and networking
 aiohttp==3.12.15
-duckdb==1.4.0
-orjson==3.11.0
 pyzmq==27.0.2
 uvloop==0.21.0
-datasets==4.1.1
+
+# Data handling
+duckdb==1.4.0
+orjson==3.11.0
+msgspec==0.19.0
 pydantic==2.12.0
 pydantic_core==2.41.1
-msgspec==0.19.0
 
-# Needed to do tokenization for OSL reporting
+# Needed for tokenization and OSL reporting
 transformers==4.57.1
 numpy==2.3.4
 datasets==4.1.1
@@ -36,3 +41,31 @@ colorama==0.4.6
 
 # Fix pytz-2024 import warning
 pytz==2025.2
+
+# ============================================================================
+# Development Dependencies
+# ============================================================================
+
+# Testing
+pytest>=7.0.0
+pytest-asyncio>=0.21.0
+pytest-cov>=4.0.0
+pytest-benchmark>=4.0.0
+pytest-timeout==2.4.0
+pytest-xdist==3.8.0
+
+# Code quality
+ruff>=0.3.0
+
+# Development tools
+pre-commit>=3.0.0
+
+# Profiling tools
+line-profiler==5.0.0
+Pympler==1.1
+
+# Documentation
+sphinx>=7.0.0
+sphinx-rtd-theme>=2.0.0
+sphinx-autodoc-typehints>=1.25.0
+myst-parser>=2.0.0