From cddb1cdf8fd85538003990dd12ab4f686d3da064 Mon Sep 17 00:00:00 2001 From: Yineng Zhang Date: Mon, 10 Feb 2025 14:12:16 +0800 Subject: [PATCH] chore: bump v0.4.2.post4 (#3459) --- benchmark/deepseek_v3/README.md | 2 +- docker/Dockerfile.rocm | 2 +- docs/developer/setup_github_runner.md | 4 ++-- docs/start/install.md | 12 ++++++------ python/pyproject.toml | 4 ++-- python/sglang/version.py | 2 +- 6 files changed, 13 insertions(+), 13 deletions(-) diff --git a/benchmark/deepseek_v3/README.md b/benchmark/deepseek_v3/README.md index 394ead65d..6d69e078c 100644 --- a/benchmark/deepseek_v3/README.md +++ b/benchmark/deepseek_v3/README.md @@ -33,7 +33,7 @@ Add [performance optimization options](#performance-optimization-options) as nee ### Using pip ```bash # Installation -pip install "sglang[all]>=0.4.2.post3" --find-links https://flashinfer.ai/whl/cu124/torch2.5/flashinfer +pip install "sglang[all]>=0.4.2.post4" --find-links https://flashinfer.ai/whl/cu124/torch2.5/flashinfer # Launch python3 -m sglang.launch_server --model deepseek-ai/DeepSeek-V3 --tp 8 --trust-remote-code diff --git a/docker/Dockerfile.rocm b/docker/Dockerfile.rocm index cfe44f1db..89b27d450 100644 --- a/docker/Dockerfile.rocm +++ b/docker/Dockerfile.rocm @@ -1,5 +1,5 @@ # Usage (to build SGLang ROCm docker image): -# docker build --build-arg SGL_BRANCH=v0.4.2.post3 -t v0.4.2.post3-rocm630 -f Dockerfile.rocm . +# docker build --build-arg SGL_BRANCH=v0.4.2.post4 -t v0.4.2.post4-rocm630 -f Dockerfile.rocm . # default base image ARG BASE_IMAGE="rocm/vllm-dev:20250114" diff --git a/docs/developer/setup_github_runner.md b/docs/developer/setup_github_runner.md index 5d8eebbd3..739267cda 100644 --- a/docs/developer/setup_github_runner.md +++ b/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:v0.4.2.post3-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:v0.4.2.post4-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:v0.4.2.post3-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:v0.4.2.post4-rocm630 /bin/bash ``` ### Step 2: Configure the runner by `config.sh` diff --git a/docs/start/install.md b/docs/start/install.md index 88a920363..e01eb1939 100644 --- a/docs/start/install.md +++ b/docs/start/install.md @@ -6,7 +6,7 @@ You can install SGLang using any of the methods below. ``` pip install --upgrade pip pip install sgl-kernel --force-reinstall --no-deps -pip install "sglang[all]>=0.4.2.post3" --find-links https://flashinfer.ai/whl/cu124/torch2.5/flashinfer/ +pip install "sglang[all]>=0.4.2.post4" --find-links https://flashinfer.ai/whl/cu124/torch2.5/flashinfer/ ``` Note: Please check the [FlashInfer installation doc](https://docs.flashinfer.ai/installation.html) to install the proper version according to your PyTorch and CUDA versions. @@ -14,7 +14,7 @@ Note: Please check the [FlashInfer installation doc](https://docs.flashinfer.ai/ ## Method 2: From source ``` # Use the last release branch -git clone -b v0.4.2.post3 https://github.com/sgl-project/sglang.git +git clone -b v0.4.2.post4 https://github.com/sgl-project/sglang.git cd sglang pip install --upgrade pip @@ -28,7 +28,7 @@ Note: To AMD ROCm system with Instinct/MI GPUs, do following instead: ``` # Use the last release branch -git clone -b v0.4.2.post3 https://github.com/sgl-project/sglang.git +git clone -b v0.4.2.post4 https://github.com/sgl-project/sglang.git cd sglang pip install --upgrade pip @@ -56,7 +56,7 @@ 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=v0.4.2.post3 -t v0.4.2.post3-rocm630 -f Dockerfile.rocm . +docker build --build-arg SGL_BRANCH=v0.4.2.post4 -t v0.4.2.post4-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 \ @@ -65,11 +65,11 @@ 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=" \ - v0.4.2.post3-rocm630 \ + v0.4.2.post4-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 v0.4.2.post3-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 v0.4.2.post4-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 diff --git a/python/pyproject.toml b/python/pyproject.toml index 830bc9575..03a71af1e 100644 --- a/python/pyproject.toml +++ b/python/pyproject.toml @@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta" [project] name = "sglang" -version = "0.4.2.post3" +version = "0.4.2.post4" description = "SGLang is yet another fast serving framework for large language models and vision language models." readme = "README.md" requires-python = ">=3.8" @@ -25,7 +25,7 @@ runtime_common = [ ] srt = [ "sglang[runtime_common]", "cuda-python", - "sgl-kernel>=0.0.3.post2", "torch", "vllm>=0.6.4.post1,<=0.7.2", + "sgl-kernel>=0.0.3.post3", "torch", "vllm>=0.6.4.post1,<=0.7.2", "flashinfer_python>=0.2.0.post2", "outlines>=0.0.44,<=0.1.11" ] diff --git a/python/sglang/version.py b/python/sglang/version.py index f5f496d7a..a298c72e9 100644 --- a/python/sglang/version.py +++ b/python/sglang/version.py @@ -1 +1 @@ -__version__ = "0.4.2.post3" +__version__ = "0.4.2.post4"