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

ROCm: bump 6.3.0 (#3259)

Browse Source
This commit is contained in:
HAI
2025-02-02 12:13:40 -08:00
committed by GitHub
parent 55f5fc68ac
commit 566d61d90f
7 changed files with 28 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
docs/start/install.md
View File

@@ -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.post1 -t v0.4.2.post1-rocm620 -f Dockerfile.rocm .
docker build --build-arg SGL_BRANCH=v0.4.2.post1 -t v0.4.2.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 \
@@ -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.post1-rocm620 \
v0.4.2.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 v0.4.2.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
drun v0.4.2.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