chore: bump v0.4.7 (#7038)

Makefile

@@ -19,7 +19,7 @@ format: check-deps ## Format modified Python files using isort and black
 FILES_TO_UPDATE = docker/Dockerfile.rocm \
                  python/pyproject.toml \
                  python/sglang/version.py \
-                 docs/developer/setup_github_runner.md \
+                 docs/references/setup_github_runner.md \
                  docs/start/install.md \
 				 benchmark/deepseek_v3/README.md
 

benchmark/deepseek_v3/README.md

@@ -33,7 +33,7 @@ Add [performance optimization options](#performance-optimization-options) as nee
 
 ```bash
 # Installation
-pip install "sglang[all]>=0.4.6.post5"
+pip install "sglang[all]>=0.4.7"
 
 # Launch
 python3 -m sglang.launch_server --model deepseek-ai/DeepSeek-V3 --tp 8 --trust-remote-code

docker/Dockerfile

@@ -37,9 +37,13 @@ RUN python3 -m pip install --upgrade pip setuptools wheel html5lib six \
        else \
          echo "Unsupported CUDA version: $CUDA_VERSION" && exit 1; \
        fi \
-    && python3 -m pip install --no-cache-dir torch --index-url https://download.pytorch.org/whl/cu${CUINDEX} \
+    && if [ "$CUDA_VERSION" = "12.4.1" ]; then \
+         python3 -m pip install --no-cache-dir torch --index-url https://download.pytorch.org/whl/cu126; \
+       else \
+         python3 -m pip install --no-cache-dir torch --index-url https://download.pytorch.org/whl/cu${CUINDEX}; \
+       fi \
     && cd sglang \
-    && python3 -m pip --no-cache-dir install -e "python[${BUILD_TYPE}]" --find-links https://flashinfer.ai/whl/cu${CUINDEX}/torch2.6/flashinfer-python \
+    && python3 -m pip --no-cache-dir install -e "python[${BUILD_TYPE}]" \
     && if [ "$CUDA_VERSION" = "12.8.1" ]; then \
          python3 -m pip install nvidia-nccl-cu12==2.26.2.post1 --force-reinstall --no-deps; \
        fi

docker/Dockerfile.rocm

@@ -1,5 +1,5 @@
 # Usage (to build SGLang ROCm docker image):
-#   docker build --build-arg SGL_BRANCH=v0.4.6.post5 -t v0.4.6.post5-rocm630 -f Dockerfile.rocm .
+#   docker build --build-arg SGL_BRANCH=v0.4.7 -t v0.4.7-rocm630 -f Dockerfile.rocm .
 
 # default base image
 ARG BASE_IMAGE="rocm/sgl-dev:vllm20250114"

docs/references/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:v0.4.6.post5-rocm630 /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:v0.4.7-rocm630 /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:v0.4.6.post5-rocm630 /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:v0.4.7-rocm630 /bin/bash
 ```
 
 ### Step 2: Configure the runner by `config.sh`

docs/start/install.md

@@ -11,7 +11,7 @@ It is recommended to use uv to install the dependencies for faster installation:
 ```bash
 pip install --upgrade pip
 pip install uv
-uv pip install "sglang[all]>=0.4.6.post5"
+uv pip install "sglang[all]>=0.4.7"
 ```
 
 **Quick Fixes to Common Problems**
@@ -27,7 +27,7 @@ uv pip install "sglang[all]>=0.4.6.post5"
 
 ```bash
 # Use the last release branch
-git clone -b v0.4.6.post5 https://github.com/sgl-project/sglang.git
+git clone -b v0.4.7 https://github.com/sgl-project/sglang.git
 cd sglang
 
 pip install --upgrade pip
@@ -42,7 +42,7 @@ Note: For AMD ROCm system with Instinct/MI GPUs, do following instead:
 
 ```bash
 # Use the last release branch
-git clone -b v0.4.6.post5 https://github.com/sgl-project/sglang.git
+git clone -b v0.4.7 https://github.com/sgl-project/sglang.git
 cd sglang
 
 pip install --upgrade pip
@@ -71,7 +71,7 @@ docker run --gpus all \
 Note: For 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=v0.4.6.post5 -t v0.4.6.post5-rocm630 -f Dockerfile.rocm .
+docker build --build-arg SGL_BRANCH=v0.4.7 -t v0.4.7-rocm630 -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 \
@@ -80,11 +80,11 @@ 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>" \
-    v0.4.6.post5-rocm630 \
+    v0.4.7-rocm630 \
     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 v0.4.6.post5-rocm630 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 v0.4.7-rocm630 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 = "0.4.6.post5"
+version = "0.4.7"
 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__ = "0.4.6.post5"
+__version__ = "0.4.7"