From b6cd903604a7439fcd082290ade83a02b164eca0 Mon Sep 17 00:00:00 2001
From: Lianmin Zheng <lianminzheng@gmail.com>
Date: Sat, 19 Oct 2024 12:58:55 -0700
Subject: [PATCH] Update readme and workflow (#1716)

---
 .github/workflows/pr-test-amd.yml | 5 +++--
 README.md                         | 2 +-
 python/sglang/README.md           | 3 ++-
 3 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/.github/workflows/pr-test-amd.yml b/.github/workflows/pr-test-amd.yml
index 27a964d29..83210fe52 100644
--- a/.github/workflows/pr-test-amd.yml
+++ b/.github/workflows/pr-test-amd.yml
@@ -14,7 +14,7 @@ on:
   workflow_dispatch:
 
 concurrency:
-  group: pr-test-${{ github.ref }}
+  group: pr-test-amd-${{ github.ref }}
   cancel-in-progress: true
 
 jobs:
@@ -28,7 +28,8 @@ jobs:
       - name: Install dependencies
         run: |
           pip install --upgrade pip
-          pip install -e "python[all]" --no-deps
+          pip install -e "python[runtime_common, test]"
+          pip install -e "python" --no-deps
 
           git clone https://github.com/merrymercy/human-eval.git
           cd human-eval
diff --git a/README.md b/README.md
index b5827f792..d4b0f140d 100644
--- a/README.md
+++ b/README.md
@@ -18,11 +18,11 @@
 - [2024/10] 🔥 The First SGLang Online Meetup ([slides](https://github.com/sgl-project/sgl-learning-materials?tab=readme-ov-file#the-first-sglang-online-meetup)).
 - [2024/09] SGLang v0.3 Release: 7x Faster DeepSeek MLA, 1.5x Faster torch.compile, Multi-Image/Video LLaVA-OneVision ([blog](https://lmsys.org/blog/2024-09-04-sglang-v0-3/)).
 - [2024/07] Faster Llama3 Serving with SGLang Runtime (vs. TensorRT-LLM, vLLM) ([blog](https://lmsys.org/blog/2024-07-25-sglang-llama3/)).
-- [2024/02] SGLang enables **3x faster JSON decoding** with compressed finite state machine ([blog](https://lmsys.org/blog/2024-02-05-compressed-fsm/)).
 
 <details>
 <summary>More</summary>
 
+- [2024/02] SGLang enables **3x faster JSON decoding** with compressed finite state machine ([blog](https://lmsys.org/blog/2024-02-05-compressed-fsm/)).
 - [2024/04] SGLang is used by the official **LLaVA-NeXT (video)** release ([blog](https://llava-vl.github.io/blog/2024-04-30-llava-next-video/)).
 - [2024/01] SGLang provides up to **5x faster inference** with RadixAttention ([blog](https://lmsys.org/blog/2024-01-17-sglang/)).
 - [2024/01] SGLang powers the serving of the official **LLaVA v1.6** release demo ([usage](https://github.com/haotian-liu/LLaVA?tab=readme-ov-file#demo)).
diff --git a/python/sglang/README.md b/python/sglang/README.md
index 78f469c74..8b59fc106 100644
--- a/python/sglang/README.md
+++ b/python/sglang/README.md
@@ -4,7 +4,8 @@
 - `srt`: The backend engine for running local models. (SRT = SGLang Runtime).
 - `test`: The test utilities.
 - `api.py`: The public APIs.
-- `bench_latency.py`: Benchmark a single static batch.
+- `bench_latency.py`: Benchmark the latency of running a single static batch.
+- `bench_server_latency.py`: Benchmark the latency of serving a single batch with a real server.
 - `bench_serving.py`: Benchmark online serving with dynamic requests.
 - `global_config.py`: The global configs and constants.
 - `launch_server.py`: The entry point for launching the local server.