EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

chore: bump v0.3.6.post3 (#2259)

Browse Source
This commit is contained in:
Yineng Zhang
2024-11-30 01:41:16 +08:00
committed by GitHub
parent afe1e46586
commit fae4e5e99a
8 changed files with 60 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/developer/setup_github_runner.md
View File

@@ -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:v0.3.6.post2-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:v0.3.6.post3-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:v0.3.6.post2-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:v0.3.6.post3-rocm620 /bin/bash
```
### Step 2: Configure the runner by `config.sh`

20
docs/start/install.md
View File

@@ -5,10 +5,7 @@ You can install SGLang using any of the methods below.
## Method 1: With pip
```
pip install --upgrade pip
pip install "sglang[all]"
# Install FlashInfer accelerated kernels (CUDA only for now)
pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/
pip install "sglang[all]" --find-links https://flashinfer.ai/whl/cu121/torch2.4/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.
@@ -16,14 +13,11 @@ Note: Please check the [FlashInfer installation doc](https://docs.flashinfer.ai/
## Method 2: From source
```
# Use the last release branch
git clone -b v0.3.6.post2 https://github.com/sgl-project/sglang.git
git clone -b v0.3.6.post3 https://github.com/sgl-project/sglang.git
cd sglang
pip install --upgrade pip
pip install -e "python[all]"
# Install FlashInfer accelerated kernels (CUDA only for now)
pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/
pip install -e "python[all]" --find-links https://flashinfer.ai/whl/cu121/torch2.4/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.
@@ -32,7 +26,7 @@ Note: To AMD ROCm system with Instinct/MI GPUs, do following instead:
```
# Use the last release branch
git clone -b v0.3.6.post2 https://github.com/sgl-project/sglang.git
git clone -b v0.3.6.post3 https://github.com/sgl-project/sglang.git
cd sglang
pip install --upgrade pip
@@ -57,7 +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=v0.3.6.post2 -t v0.3.6.post2-rocm620 -f Dockerfile.rocm .
docker build --build-arg SGL_BRANCH=v0.3.6.post3 -t v0.3.6.post3-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 \
@@ -66,11 +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>" \
v0.3.6.post2-rocm620 \
v0.3.6.post3-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 v0.3.6.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
drun v0.3.6.post3-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