-
Notifications
You must be signed in to change notification settings - Fork 89
Releases: hpcaitech/FastFold
Releases · hpcaitech/FastFold
FastFold v0.2.0
@oahzxl
oahzxl
930a58a
This commit was created on GitHub.com and signed with GitHub’s verified signature.
The key has expired.
Overview
Hi, here is FastFold v0.2.0. Compared to the previous version, now we inference faster and with less memory and support multimer inference.
What's Changed
- Save up to 75% GPU memory, able to inference sequence containing more than 10000 residues in bf16.
- Better softmax and layernorm kernel optimization based on Triton, at least 25% faster than previous version.
- Faster data processing, about 3 times faster on monomer, about 3N times faster on multimer with N sequence.
- Support multimer inference.
Installation
- Build from source
- Conda (recommended)
- Pypi
- Docker
Have a nice trip!
Assets 2
1 person reacted
FastFold v0.1.0
Overview
Hi, here is FastFold v0.1.0. Compared to the previous version, now you can process the data much faster. Besides, you can use pip install to install FastFold now. If you want to use docker, there is one for you.
Features we have
- Excellent kernel performance on GPU platform
- Supporting Dynamic Axial Parallelism(DAP)
- Break the memory limit of single GPU and reduce the overall training time
- DAP can significantly speed up inference and make ultra-long sequence inference possible
- Ease of use
- Huge performance gains with a few lines changes
- You don't need to care about how the parallel part is implemented
- Faster data processing, about 3x times faster than the original way
Installation ways for you
- Build from source
- Conda (recommended)
- Pypi
- Docker
Have a nice trip!
Assets 2
1 person reacted
FastFold v0.1.0-beta
0.1.0-beta