Update README.md

README.md

@@ -81,45 +81,52 @@ We evaluate the quantized models using several datasets. The FP8 quantized model
 #### Install our SGLang
 ```bash
 pip install uv
+
 uv venv ~/my_ling_env
+
 source ~/my_ling_env/bin/activate
+
 git clone -b ling_v3_support https://github.com/inclusionAI/sglang_ling_v3.git
-cd sglang
+
+cd sglang_ling_v3
+
 pip install --upgrade pip
+
 pip install -e "python"
 ```
 
 #### Run Inference
-Here is the example to run Ling-3.0-flash with 4 GPUs, where the master node IP is `${MASTER_IP}` and server port is `${PORT}`:
+Here is an example to run Ling-3.0-flash with 4 GPUs, where the master node IP is `${MASTER_IP}` and server port is `${PORT}`:
 
 **Server**
 
-As our model is trained with MTP, we recommend to turn on MTP (i.e., --speculative-algorithm NEXTN) in inference for lower latency.
+Since the model is trained with MTP, we recommend enabling MTP during inference (i.e., --speculative-algorithm NEXTN) for lower latency.
 
 ```bash
 export SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1
+export SGLANG_JIT_DEEPGEMM_PRECOMPILE=1
+export SGLANG_ENABLE_SPEC_V2=1
 python -m sglang.launch_server \
     --model-path $MODEL_PATH \
     --dist-init-addr $MASTER_IP:2345 \
     --port $PORT \
     --nnodes 1 \
     --mem-fraction-static 0.8 \
-    --max-running-requests 64 \
-    --tp-size 4 \
+    --max-running-requests 32 \
+    --tp-size 2 \
     --chunked-prefill-size 8192 \
-    --allow-auto-output-truncate \
     --tool-call-parser ling3 \
     --reasoning-parser ling3 \
     --context-length 262144 \
     --speculative-algorithm NEXTN \
-    --max-mamba-cache-size 320 \
+    --max-mamba-cache-size 160 \
     --enable-fp32-lm-head \
     --disable-shared-experts-fusion
 ```
 
 **Client**
 
-It is recommended to use the sampling params (<font style="color:rgb(16, 18, 20);">`temperature=0.6, top_p=0.95, top_k=20`</font>) and turn on `enable_thinking`for better performance.
+We recommend using the sampling parameters `temperature=0.6`, `top_p=0.95`, and `top_k=20`, and enabling `enable_thinking` for better performance.
 
 ```bash
 curl -s http://${MASTER_IP}:${PORT}/v1/chat/completions \
@@ -150,7 +157,7 @@ Here is the example to run Ling-3.0-flash with 4 GPUs, where the server port is
 
 **Server**
 
-As our model is trained with MTP, we recommend to turn on MTP (i.e., --speculative-config) in inference for lower latency.
+Since the model is trained with MTP, we recommend enabling MTP during inference (i.e., --speculative-config) for lower latency.
 
 ```bash
 vllm serve "$MODEL_PATH" \
@@ -169,7 +176,7 @@ vllm serve "$MODEL_PATH" \
 
 **Client**
 
-It is recommended to use the sampling params (<font style="color:rgb(16, 18, 20);">`temperature=0.6, top_p=0.95, top_k=20`</font>) and turn on `enable_thinking`for better performance.
+We recommend using the sampling parameters `temperature=0.6`, `top_p=0.95`, and `top_k=20`, and enabling `enable_thinking` for better performance.
 
 ```bash
 curl -s http://${MASTER_IP}:${PORT}/v1/chat/completions \