[docs] major SGL Model Gateway documentation update

[slin1237]

• Rename docs/advanced_features/router.md to sgl_model_gateway.md

• Add comprehensive documentation for new features:

  • Tokenization endpoints (/v1/tokenize, /v1/detokenize)
  • Tokenizer management APIs (/v1/tokenizers)
  • Parser endpoints (/parse/reasoning, /parse/function_call)
  • gRPC embedding support
  • Expanded metrics documentation (40+ Prometheus metrics)
  • OpenTelemetry tracing integration

• Update sgl-model-gateway/README.md with:

  • New feature highlights for tokenization and parsing APIs
  • Detailed tokenization endpoint examples
  • Parser endpoint documentation with supported parsers
  • Expanded observability section with metric categories
  • OpenTelemetry configuration details

• Update docs/index.rst to reference new filename

• Add TLS (HTTPS) documentation for gateway server

  • --tls-cert-path and --tls-key-path configuration
  • rustls with ring crypto provider details

• Add mTLS documentation for worker communication

  • --client-cert-path, --client-key-path, --ca-cert-path flags
  • Multiple CA certificate support
  • TCP keepalive configuration

• Update both README.md and sgl_model_gateway.md with:

  • Full TLS configuration examples
  • Parameter reference tables
  • Security configuration guidance

• Add TLS Configuration section to Configuration Reference

• Update Table of Contents with TLS subsections

• Security: TLS checklist and production security best practices

• High Availability:

  • Multi-replica architecture diagram
  • Trade-offs table (radix tree, circuit breaker, rate limiting)
  • Cache hit reduction (10-20%) with multiple replicas
  • Horizontal vs vertical scaling guidance
  • Session affinity recommendations

• Performance:

  • gRPC mode recommendation for high throughput
  • Performance tuning table with parameter recommendations
  • Benefits of native Rust tokenization

• Kubernetes Deployment:

  • Pod labeling examples for service discovery
  • Regular and PD mode worker deployments
  • RBAC configuration for pod watching
  • PD mode with bootstrap port annotations

• Monitoring with PromQL:

  • Request rate and latency queries
  • Worker health monitoring
  • Circuit breaker status tracking
  • Inference performance metrics (TTFT, TPOT)
  • Rate limiting and queuing metrics
  • MCP tool execution monitoring
  • Example Prometheus alerting rules

  Add comprehensive documentation for writing custom WASM middleware modules
  including authentication, rate limiting, and request logging examples.
  Documents the WIT interface, deployment process, and runtime configuration.

Checklist

• Format your code according to the Format code with pre-commit.
• Add unit tests according to the Run and add unit tests.
• Update documentation according to Write documentations.
• Provide accuracy and speed benchmark results according to Test the accuracy and Benchmark the speed.
• Follow the SGLang code style guidance.
• Work with maintainers to merge your PR. See the PR Merge Process

[gemini-code-assist]

Warning

You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again!