Files
ROCm/docs/data/how-to/rocm-for-ai/inference/sglang-benchmark-models.yaml

17 lines
636 B
YAML

dockers:
- pull_tag: lmsysorg/sglang:v0.4.5-rocm630
docker_hub_url: https://hub.docker.com/layers/lmsysorg/sglang/v0.4.5-rocm630/images/sha256-63d2cb760a237125daf6612464cfe2f395c0784e21e8b0ea37d551cd10d3c951
components:
ROCm: 6.3.0
SGLang: 0.4.5 (0.4.5-rocm)
PyTorch: 2.6.0a0+git8d4926e
model_groups:
- group: DeepSeek
tag: deepseek
models:
- model: DeepSeek-R1-Distill-Qwen-32B
mad_tag: pyt_sglang_deepseek-r1-distill-qwen-32b
model_repo: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
url: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
precision: bfloat16