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

chore: bump v0.4.2.post1 (#3233)

Browse Source
This commit is contained in:
Yineng Zhang
2025-01-31 20:35:55 +08:00
committed by GitHub
parent b49d6d0fee
commit cf0f7eafe6
5 changed files with 10 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
docs/start/install.md
View File

@@ -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 https://github.com/sgl-project/sglang.git
git clone -b v0.4.2.post1 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 https://github.com/sgl-project/sglang.git
git clone -b v0.4.2.post1 https://github.com/sgl-project/sglang.git
cd sglang
pip install --upgrade pip
@@ -54,7 +54,7 @@ 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 -t v0.4.2-rocm620 -f Dockerfile.rocm .
docker build --build-arg SGL_BRANCH=v0.4.2.post1 -t v0.4.2.post1-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 \
@@ -63,11 +63,11 @@ 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>" \
v0.4.2-rocm620 \
v0.4.2.post1-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 v0.4.2-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 v0.4.2.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
```
## Method 4: Using docker compose