From 753d5aa340fe72cd071bb0ab10aa07cb9caedd34 Mon Sep 17 00:00:00 2001
From: torchspec-bot <262938024+torchspec-bot@users.noreply.github.com>
Date: Sat, 7 Mar 2026 14:09:47 -0800
Subject: [PATCH] [Doc] update README

---
 README.md | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/README.md b/README.md
index 20af846..5f1362c 100644
--- a/README.md
+++ b/README.md
@@ -14,19 +14,19 @@ TorchSpec supports two inference backends:
 
 | Backend | Best For | Installation |
 |---------|----------|--------------|
-| **SGLang** | Production workloads, high throughput | `./tools/build_conda.sh 1 sglang` (default) |
 | **vLLM** | Flexibility, easier deployment | `./tools/build_conda.sh 1 vllm` |
+| **SGLang** | Production workloads, high throughput | `./tools/build_conda.sh 1 sglang` |
 | **Both** | Development, comparison testing | `./tools/build_conda.sh 1 both` |
 
 ### Quick Setup
 
 ```bash
-# Install with SGLang (default)
-./tools/build_conda.sh
+# Install with vLLM
+./tools/build_conda.sh 1 vllm
 micromamba activate torchspec
 
-# Or install with vLLM
-./tools/build_conda.sh 1 vllm
+# Or install with SGLang
+./tools/build_conda.sh
 micromamba activate torchspec
 ```
 
@@ -43,14 +43,14 @@ pip install -e ".[fa]"
 
 ### Backend-Specific Usage
 
-**SGLang (default):**
+**vLLM:**
 ```bash
-./examples/qwen3-8b-single-node/run.sh
+./examples/qwen3-8b-single-node/run.sh --config configs/vllm_qwen3_8b.yaml
 ```
 
-**vLLM:**
+**SGLang:**
 ```bash
-./examples/qwen3-8b-single-node/run.sh --config configs/vllm_qwen3_8b.yaml
+./examples/qwen3-8b-single-node/run.sh
 ```
 
 TorchSpec uses vLLM's **Worker Extension** mechanism to hook into the model's forward pass and capture hidden states directly in the worker processes. This avoids RPC serialization issues and enables reliable hidden states extraction.