refactor: split LLM Inference and Serving into Local LLM Inference and LLM Serving

Local runners (ollama, llama-cpp-python, mlx-lm) and production serving engines (vllm, sglang) answer different needs, and one use case could not hold both at the cap. The old page redirects to LLM Serving.

Co-Authored-By: Claude <noreply@anthropic.com>

README.md

@@ -168,10 +168,11 @@ _Libraries for building AI applications, LLM integrations, and autonomous agents
 - Pre-trained Models
   - [transformers](https://github.com/huggingface/transformers) - The model-definition framework for pretrained models in text, computer vision, audio, video, and multimodal tasks, for inference and training.
   - [sentence-transformers](https://github.com/huggingface/sentence-transformers) - Compute embeddings, run retrieval, and rerank results with pretrained and fine-tuned models.
-- LLM Inference and Serving
+- Local LLM Inference
+  - [mlx-lm](https://github.com/ml-explore/mlx-lm) - Run and fine-tune large language models on Apple Silicon with MLX.
+- LLM Serving
   - [vllm](https://github.com/vllm-project/vllm) - A high-throughput and memory-efficient inference and serving engine for LLMs.
   - [sglang](https://github.com/sgl-project/sglang) - A high-performance serving framework for large language models and multimodal models.
-  - [mlx-lm](https://github.com/ml-explore/mlx-lm) - Run and fine-tune large language models on Apple Silicon with MLX.
 - LLM Gateways
   - [litellm](https://github.com/BerriAI/litellm) - Call 100+ LLMs using OpenAI format.
 - Image and Video Generation

website/data/redirects.json

@@ -1,5 +1,6 @@
 {
   "/categories/": "/",
+  "/categories/ai-and-agents/llm-inference-and-serving/": "/categories/ai-and-agents/llm-serving/",
   "/categories/ai-and-agents/pre-trained-models-and-inference/": "/categories/ai-and-agents/pre-trained-models/",
   "/categories/cli-development/cli-development/": "/categories/cli-development/",
   "/categories/cli-tools/productivity-tools/": "/categories/cli-tools/",