Unverified Commit e5f13356 authored by Biswa Panda's avatar Biswa Panda Committed by GitHub
Browse files

docs: add gpu details for model recipes (#3594)

parent 4c4130e3
# Dynamo model serving recipes # Dynamo model serving recipes
| Model family | Backend | Mode | Deployment | Benchmark | | Model family | Backend | Mode | GPU | Deployment | Benchmark |
|---------------|---------|---------------------|------------|-----------| |---------------|---------|---------------------|-------|------------|-----------|
| llama-3-70b | vllm | agg | ✓ | ✓ | | llama-3-70b | vllm | agg | H100, H200 | ✓ | ✓ |
| llama-3-70b | vllm | disagg-multi-node | ✓ | ✓ | | llama-3-70b | vllm | disagg-multi-node | H100, H200 | ✓ | ✓ |
| llama-3-70b | vllm | disagg-single-node | ✓ | ✓ | | llama-3-70b | vllm | disagg-single-node | H100, H200 | ✓ | ✓ |
| oss-gpt | trtllm | aggregated | ✓ | | | DeepSeek-R1 | sglang | disaggregated | H200 | ✓ | 🚧 |
| DeepSeek-R1 | sglang | disaggregated | ✓ | 🚧 | | oss-gpt | trtllm | aggregated | GB200 | ✓ | |
## Prerequisites ## Prerequisites
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment