chore: bump v0.4.0.post2 (#2525)

.github/workflows/release-docker.yml

@@ -58,7 +58,7 @@ jobs:
           docker build . -f docker/Dockerfile --build-arg CUDA_VERSION=${{ matrix.cuda_version }} --build-arg BUILD_TYPE=${{ matrix.build_type }} -t lmsysorg/sglang:${tag}${tag_suffix} --no-cache
           docker push lmsysorg/sglang:${tag}${tag_suffix}
 
-          if [ "${{ matrix.cuda_version }}" = "12.1.1" ]; then
+          if [ "${{ matrix.cuda_version }}" = "12.4.1" ]; then
             docker tag lmsysorg/sglang:${tag}${tag_suffix} lmsysorg/sglang:latest${tag_suffix}
             docker push lmsysorg/sglang:latest${tag_suffix}
           fi

docker/Dockerfile.rocm

@@ -1,5 +1,5 @@
 # Usage (to build SGLang ROCm docker image):
-#   docker build --build-arg SGL_BRANCH=v0.4.0.post1 -t v0.4.0.post1-rocm620 -f Dockerfile.rocm .
+#   docker build --build-arg SGL_BRANCH=v0.4.0.post2 -t v0.4.0.post2-rocm620 -f Dockerfile.rocm .
 
 # default base image
 ARG BASE_IMAGE="rocm/vllm-dev:20241022"

docs/developer/setup_github_runner.md

@@ -11,9 +11,9 @@ docker pull nvidia/cuda:12.1.1-devel-ubuntu22.04
 # Nvidia
 docker run --shm-size 128g -it -v /tmp/huggingface:/hf_home --gpus all nvidia/cuda:12.1.1-devel-ubuntu22.04 /bin/bash
 # AMD
-docker run --rm --device=/dev/kfd --device=/dev/dri --group-add video --shm-size 128g -it -v /tmp/huggingface:/hf_home lmsysorg/sglang:v0.4.0.post1-rocm620 /bin/bash
+docker run --rm --device=/dev/kfd --device=/dev/dri --group-add video --shm-size 128g -it -v /tmp/huggingface:/hf_home lmsysorg/sglang:v0.4.0.post2-rocm620 /bin/bash
 # AMD just the last 2 GPUs
-docker run --rm --device=/dev/kfd --device=/dev/dri/renderD176 --device=/dev/dri/renderD184 --group-add video --shm-size 128g -it -v /tmp/huggingface:/hf_home lmsysorg/sglang:v0.4.0.post1-rocm620 /bin/bash
+docker run --rm --device=/dev/kfd --device=/dev/dri/renderD176 --device=/dev/dri/renderD184 --group-add video --shm-size 128g -it -v /tmp/huggingface:/hf_home lmsysorg/sglang:v0.4.0.post2-rocm620 /bin/bash
 ```
 
 ### Step 2: Configure the runner by `config.sh`

docs/start/install.md

@@ -13,7 +13,7 @@ Note: Please check the [FlashInfer installation doc](https://docs.flashinfer.ai/
 ## Method 2: From source
 ```
 # Use the last release branch
-git clone -b v0.4.0.post1 https://github.com/sgl-project/sglang.git
+git clone -b v0.4.0.post2 https://github.com/sgl-project/sglang.git
 cd sglang
 
 pip install --upgrade pip
@@ -26,7 +26,7 @@ Note: To AMD ROCm system with Instinct/MI GPUs, do following instead:
 
 ```
 # Use the last release branch
-git clone -b v0.4.0.post1 https://github.com/sgl-project/sglang.git
+git clone -b v0.4.0.post2 https://github.com/sgl-project/sglang.git
 cd sglang
 
 pip install --upgrade pip
@@ -51,7 +51,7 @@ docker run --gpus all \
 Note: To AMD ROCm system with Instinct/MI GPUs, it is recommended to use `docker/Dockerfile.rocm` to build images, example and usage as below:
 
 ```bash
-docker build --build-arg SGL_BRANCH=v0.4.0.post1 -t v0.4.0.post1-rocm620 -f Dockerfile.rocm .
+docker build --build-arg SGL_BRANCH=v0.4.0.post2 -t v0.4.0.post2-rocm620 -f Dockerfile.rocm .
 
 alias drun='docker run -it --rm --network=host --device=/dev/kfd --device=/dev/dri --ipc=host \
     --shm-size 16G --group-add video --cap-add=SYS_PTRACE --security-opt seccomp=unconfined \
@@ -60,11 +60,11 @@ alias drun='docker run -it --rm --network=host --device=/dev/kfd --device=/dev/d
 drun -p 30000:30000 \
     -v ~/.cache/huggingface:/root/.cache/huggingface \
     --env "HF_TOKEN=<secret>" \
-    v0.4.0.post1-rocm620 \
+    v0.4.0.post2-rocm620 \
     python3 -m sglang.launch_server --model-path meta-llama/Llama-3.1-8B-Instruct --host 0.0.0.0 --port 30000
 
 # Till flashinfer backend available, --attention-backend triton --sampling-backend pytorch are set by default
-drun v0.4.0.post1-rocm620 python3 -m sglang.bench_one_batch --batch-size 32 --input 1024 --output 128 --model amd/Meta-Llama-3.1-8B-Instruct-FP8-KV --tp 8 --quantization fp8
+drun v0.4.0.post2-rocm620 python3 -m sglang.bench_one_batch --batch-size 32 --input 1024 --output 128 --model amd/Meta-Llama-3.1-8B-Instruct-FP8-KV --tp 8 --quantization fp8
 ```
 
 ## Method 4: Using docker compose

python/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "sglang"
-version = "0.4.0.post1"
+version = "0.4.0.post2"
 description = "SGLang is yet another fast serving framework for large language models and vision language models."
 readme = "README.md"
 requires-python = ">=3.8"

python/sglang/version.py

@@ -1 +1 @@
-__version__ = "0.4.0.post1"
+__version__ = "0.4.0.post2"