Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update README.md #322

Merged
merged 2 commits into from
Dec 12, 2024
Merged

Update README.md #322

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
50dfe93
Update README.md
t-parry Dec 12, 2024
921b3b2
Merge branch 'main' into patch-2
gshtras Dec 12, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 5 additions & 6 deletions docs/dev-docker/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,11 +10,11 @@ This documentation shows some reference performance numbers and the steps to rep

It includes:

- ROCm™ 6.2.2
- ROCm™ 6.3

- vLLM 0.6.3

- PyTorch 2.5dev (nightly)
- PyTorch 2.6dev (nightly)

## System configuration

Expand All @@ -23,7 +23,7 @@ The performance data below was measured on a server with MI300X accelerators wit
| System | MI300X with 8 GPUs |
|---|---|
| BKC | 24.13 |
| ROCm | version ROCm 6.2.2 |
| ROCm | version ROCm 6.3 |
| amdgpu | build 2009461 |
| OS | Ubuntu 22.04 |
| Linux Kernel | 5.15.0-117-generic |
Expand All @@ -45,9 +45,8 @@ You can pull the image with `docker pull rocm/vllm-dev:main`

### What is New

- MoE optimizations for Mixtral 8x22B, FP16
- Llama 3.2 stability improvements
- Llama 3.3 support
- ROCm 6.3 support
- Potential bug with Tunable Ops not saving due to a PyTorch issue


Gemms are tuned using PyTorch's Tunable Ops feature (https://github.com/pytorch/pytorch/blob/main/aten/src/ATen/cuda/tunable/README.md)
Expand Down
Loading