pub_soft/alphafold3
3
0
Fork 0
mirror of https://github.com/google-deepmind/alphafold3.git synced 2026-06-02 11:54:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

Use --run_*=false instead of --norun_* in docs.

Browse Source 
PiperOrigin-RevId: 886655698
Change-Id: If37e31d659c5b31856ce9bb6cb215b49bb7a96f8
This commit is contained in:
Augustin Zidek
2026-03-20 02:19:01 -07:00
committed by Copybara-Service
parent 608edb684d
commit 02650a5ded
1 changed files with 9 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
docs/performance.md
View File

@@ -18,11 +18,11 @@ utilisation. This can be useful for:
### Data Pipeline Only
Launch `run_alphafold.py` with `--norun_inference` to generate Multiple Sequence
Alignments (MSAs) and templates, without running featurisation and model
inference. This stage can be quite costly in terms of runtime, CPU, and RAM use.
The output will be JSON files augmented with MSAs and templates that can then be
directly used as input for running inference.
Launch `run_alphafold.py` with `--run_inference=false` to generate Multiple
Sequence Alignments (MSAs) and templates, without running featurisation and
model inference. This stage can be quite costly in terms of runtime, CPU, and
RAM use. The output will be JSON files augmented with MSAs and templates that
can then be directly used as input for running inference.
### Pre-computing and reusing MSA and templates
@@ -62,10 +62,10 @@ similar issues).
### Featurisation and Model Inference Only
Launch `run_alphafold.py` with `--norun_data_pipeline` to skip the data pipeline
and run only featurisation and model inference. This stage requires the input
JSON file to contain pre-computed MSAs and templates (or they must be explicitly
set to empty if you want to run MSA and template free).
Launch `run_alphafold.py` with `--run_data_pipeline=false` to skip the data
pipeline and run only featurisation and model inference. This stage requires the
input JSON file to contain pre-computed MSAs and templates (or they must be
explicitly set to empty if you want to run MSA and template free).
## Data Pipeline