From e782eb7e6a9af1e4b81adf7459f737b29fb388ea Mon Sep 17 00:00:00 2001 From: Yineng Zhang Date: Mon, 17 Feb 2025 21:58:19 +0800 Subject: [PATCH] chore: bump v0.4.3.post1 (#3638) --- docker/Dockerfile.rocm | 2 +- docs/developer/setup_github_runner.md | 4 ++-- docs/start/install.md | 12 ++++++------ python/pyproject.toml | 2 +- python/sglang/version.py | 2 +- test/srt/test_mla.py | 2 ++ 6 files changed, 13 insertions(+), 11 deletions(-) diff --git a/docker/Dockerfile.rocm b/docker/Dockerfile.rocm index ff637a0a2..983eb6a95 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=v0.4.3 -t v0.4.3-rocm630 -f Dockerfile.rocm . +# docker build --build-arg SGL_BRANCH=v0.4.3.post1 -t v0.4.3.post1-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 89eeaeafc..e57b627cd 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:v0.4.3-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:v0.4.3.post1-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:v0.4.3-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:v0.4.3.post1-rocm630 /bin/bash ``` ### Step 2: Configure the runner by `config.sh` diff --git a/docs/start/install.md b/docs/start/install.md index 5bfdec0e6..8f37c5bb5 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. For running DeepSeek V3/R ``` pip install --upgrade pip pip install sgl-kernel --force-reinstall --no-deps -pip install "sglang[all]>=0.4.3" --find-links https://flashinfer.ai/whl/cu124/torch2.5/flashinfer-python +pip install "sglang[all]>=0.4.3.post1" --find-links https://flashinfer.ai/whl/cu124/torch2.5/flashinfer-python ``` Note: SGLang currently uses torch 2.5, so you need to install the flashinfer version for torch 2.5. If you want to install flashinfer separately, please refer to [FlashInfer installation doc](https://docs.flashinfer.ai/installation.html). Please note that the package currently used by FlashInfer is named `flashinfer-python`, not `flashinfer`. @@ -19,7 +19,7 @@ If you experience an error like `OSError: CUDA_HOME environment variable is not ## Method 2: From source ``` # Use the last release branch -git clone -b v0.4.3 https://github.com/sgl-project/sglang.git +git clone -b v0.4.3.post1 https://github.com/sgl-project/sglang.git cd sglang pip install --upgrade pip @@ -35,7 +35,7 @@ Note: To AMD ROCm system with Instinct/MI GPUs, do following instead: ``` # Use the last release branch -git clone -b v0.4.3 https://github.com/sgl-project/sglang.git +git clone -b v0.4.3.post1 https://github.com/sgl-project/sglang.git cd sglang pip install --upgrade pip @@ -63,7 +63,7 @@ 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=v0.4.3 -t v0.4.3-rocm630 -f Dockerfile.rocm . +docker build --build-arg SGL_BRANCH=v0.4.3.post1 -t v0.4.3.post1-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 \ @@ -72,11 +72,11 @@ 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=" \ - v0.4.3-rocm630 \ + v0.4.3.post1-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 v0.4.3-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 v0.4.3.post1-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 37adc37d2..837bb090a 100644 --- a/python/pyproject.toml +++ b/python/pyproject.toml @@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta" [project] name = "sglang" -version = "0.4.3" +version = "0.4.3.post1" description = "SGLang is yet another fast serving framework for large language models and vision language models." readme = "README.md" requires-python = ">=3.8" diff --git a/python/sglang/version.py b/python/sglang/version.py index f6b7e267c..8d25b4170 100644 --- a/python/sglang/version.py +++ b/python/sglang/version.py @@ -1 +1 @@ -__version__ = "0.4.3" +__version__ = "0.4.3.post1" diff --git a/test/srt/test_mla.py b/test/srt/test_mla.py index c7016eb14..0bc64ea3e 100644 --- a/test/srt/test_mla.py +++ b/test/srt/test_mla.py @@ -141,6 +141,8 @@ class TestDeepseekV3MTP(unittest.TestCase): metrics = run_eval_few_shot_gsm8k(args) print(metrics) + self.assertGreater(metrics["accuracy"], 0.62) + if __name__ == "__main__": unittest.main()