Add Gemma2 (#592)

docs/model_support.md

@@ -6,5 +6,13 @@ You can learn from existing model implementations and create new files for the n
 
 Another valuable resource is the vLLM model implementations. vLLM has extensive coverage of models, and SGLang has reused vLLM for most parts of the model implementations. This similarity makes it easy to port many models from vLLM to SGLang.
 
-1. Compare these two files [SGLang LLaMA Implementation](https://github.com/sgl-project/sglang/blob/main/python/sglang/srt/models/llama2.py) and [vLLM LLaMA Implementation](https://github.com/vllm-project/vllm/blob/main/vllm/model_executor/models/llama.py). This comparison will help you understand how to convert a model implementation from vLLM to SGLang. The major difference is the replacement of PagedAttention with RadixAttention. The other parts are almost identical.
+1. Compare these two files [SGLang LLaMA Implementation](https://github.com/sgl-project/sglang/blob/main/python/sglang/srt/models/llama2.py) and [vLLM LLaMA Implementation](https://github.com/vllm-project/vllm/blob/main/vllm/model_executor/models/llama.py). This comparison will help you understand how to convert a model implementation from vLLM to SGLang. The major difference is the replacement of PagedAttention with RadixAttention. The other parts are almost identical. Specifically,
+  - Replace `Attention` with `RadixAttention`.
+  - Replace vllm's `LogitsProcessor` with SGLang's `LogitsProcessor`.
+  - Remove `Sample`.
+  - Change `forward()` functions, and add `input_metadata`.
+  - Add `EntryClass` at the end.
+  - Test correctness by comparing the final logits and outputs of two following commands:
+    - `python3 playground/reference_hf.py --model [new model]`
+    - `python3 -m sglang.bench_latency --model [new model] --correct --output-len 16`
 2. Convert models from vLLM to SGLang by visiting the [vLLM Models Directory](https://github.com/vllm-project/vllm/tree/main/vllm/model_executor/models).