Updated README.md to include the latest command and performance.

README.md

@@ -15,11 +15,14 @@ This quant modified some of the model code to fix an overflow issue when using f
 
 To serve using vLLM with 8x 80GB GPUs, use the following command:
 ```sh
-python -m vllm.entrypoints.openai.api_server --host 0.0.0.0 --port 12345 --max-model-len 65536 --trust-remote-code --tensor-parallel-size 8 --quantization moe_wna16 --gpu-memory-utilization 0.97 --kv-cache-dtype fp8_e5m2 --calculate-kv-scales --served-model-name deepseek-reasoner --model cognitivecomputations/DeepSeek-R1-AWQ
+VLLM_WORKER_MULTIPROC_METHOD=spawn python -m vllm.entrypoints.openai.api_server --host 0.0.0.0 --port 12345 --max-model-len 65536 --max-num-batched-tokens 65536 --trust-remote-code --tensor-parallel-size 8 --gpu-memory-utilization 0.97 --dtype float16 --served-model-name deepseek-reasoner --model cognitivecomputations/DeepSeek-R1-AWQ
 ```
-The max model length flag ensures that KV cache usage won't be higher than available memory, the `moe_wna16` kernel doubles the inference speed, but you must build vLLM from source as of 2025/2/3. \
-You can download the wheel I built for PyTorch 2.6, Python 3.12 by clicking [here](https://huggingface.co/x2ray/wheels/resolve/main/vllm-0.7.1.dev69%2Bg4f4d427a.d20220101.cu126-cp312-cp312-linux_x86_64.whl).
+You can download the wheel I built for PyTorch 2.6, Python 3.12 by clicking [here](https://huggingface.co/x2ray/wheels/resolve/main/vllm-0.7.3.dev187%2Bg0ff1a4df.d20220101.cu126-cp312-cp312-linux_x86_64.whl).
 
 Inference speed with batch size 1 and short prompt:
-- 8x H100: 34 TPS
-- 8x A100: 27 TPS
+- 8x H100: 48 TPS
+- 8x A100: 38 TPS
+
+Note:
+- Inference speed will be better than FP8 at low batch size but worse than FP8 at high batch size, this is the nature of low bit quantization.
+- vLLM supports MLA for AWQ now, you can run this model with full context length on just 8x 80GB GPUs.