branch: RFdiffusion:main 「№19」
Commited by: Rachel Clune
GitHub commit link: 「2d0c003df46b9db4」
Difference from previous tested commit:  code diff
Commit date: 2026-04-24 14:47:30
rfd

Adding files for the soon-to-be-released RFdiffusion video tutorial (#452) The materials were created by Diego Lopez Mateos, Matthew Hvasta, and Kush Narang for the Tutorial Hackathon track of the 2026 Megathon event.

...
Test: ubuntu-20.04.clang.python39.rfd

 View log

Loading...

 View log in dialog  View log in log in separate window


branch: RFdiffusion:main 「№18」
Commited by: Leonardo Marino-Ramirez
GitHub commit link: 「529b756796001f54」
Difference from previous tested commit:  code diff
Commit date: 2026-04-24 12:41:07
rfd

feat: add inference.empty_cache_per_design flag to reduce CUDA allocator fragmentation (#451) ## Problem When running RFdiffusion with variable-length contigs (e.g. `contigmap.contigs=[A1-469/0 1-50]`) over hundreds or thousands of designs, per-worker VRAM grows steadily from ~7 GB to 10–13 GB per process. This limits how many workers can run in parallel on a single GPU before exhausting VRAM. Root cause: PyTorch's CUDA caching allocator accumulates fragmented memory blocks across designs. With variable-length contigs each design allocates differently-sized tensors; freed blocks are cached but cannot be reused for different-sized allocations, causing steady VRAM growth. ## Fix Add an optional `inference.empty_cache_per_design` flag (default `False`, opt-in) that calls `torch.cuda.empty_cache()` at the end of each design iteration. This releases all unused cached CUDA memory blocks back to the CUDA memory manager, keeping each worker near its initial VRAM footprint for the full run. ### Changes **`config/inference/base.yaml`** ```yaml write_trajectory: True empty_cache_per_design: False # NEW ``` **`scripts/run_inference.py`** — after the trajectory/PDB write block, before `log.info`: ```python if conf.inference.empty_cache_per_design and torch.cuda.is_available(): torch.cuda.empty_cache() log.info(f"Finished design in {(time.time()-start_time)/60:.2f} minutes") ``` ## Measured impact Tested on NVIDIA RTX 5090 32 GB running a long PPI campaign with variable-length contigs: | Setting | Per-worker VRAM (steady-state) | |---------|-------------------------------| | Without fix | 8–13 GB (grows over run) | | With `empty_cache_per_design=True` | ~5.2 GB (stable) | This allowed raising the number of parallel workers from 3 to 5 on a 32 GB GPU. ## Why opt-in `torch.cuda.empty_cache()` adds a small per-design overhead (~1–2 ms) and is only beneficial for long runs with variable-length contigs. For short runs or fixed-length designs there is no fragmentation issue, so the default remains `False` to preserve existing behavior. ## Testing All 20 applicable tests in `tests/test_diffusion.py` pass with this change. The one skipped test (`design_ppi_scaffolded`) fails due to a missing `ppi_scaffolds/` directory in the test fixture — a pre-existing issue unrelated to this PR. ## Notes - Placement is after both the PDB write (`writepdb`) and the optional trajectory block — every consumer of `denoised_xyz_stack` / `px0_xyz_stack` has already finished before the cache is cleared. - This does not affect memory held by live tensors — only frees cached-but-unused blocks. - Compatible with all existing RFdiffusion design modes (PPI, motif scaffolding, unconditional).

...
Test: ubuntu-20.04.clang.python39.rfd

 View log

Loading...

 View log in dialog  View log in log in separate window


branch: RFdiffusion:main 「№17」
Commited by: Hope Woods
GitHub commit link: 「9535f1938203a249」
Difference from previous tested commit:  code diff
Commit date: 2025-11-20 11:02:33
rfd

Updated "Fixed issues with designing in scaffoldguided mode" original PR 386 (#426) The original PR for this was #386 from [OrangeCatzhang](https://github.com/OrangeCatzhang). This PR is to fix the error "AttributeError: 'bool' object has no attribute 'scaffold_list'" when running in scaffoldguided mode. The first error is fixed by passing the full composed config object (conf) into BlockAdjacency instead of passing the scaffoldguided sub-node. BlockAdjacency expects the full config and to access conf.scaffoldguided.<fields> internally, so passing the sub-node caused self.conf.scaffoldguided to resolve to the nested boolean field (scaffoldguided.scaffoldguided), which produced the AttributeError when code tried to read .scaffold_list. Passing teh full conf fixes that mismatch. The other fix is to add initialization of cyclic_reses to ScaffoldedSampler. I have slightly updated what was in the original PR to avoid code duplication. I added a helper function to the Sampler class and then call that in both Sampler and ScaffoldedSampler to initialize cyclic_reses. I also removed the changes to the scaffoldedguided flag from the original PR, so the CLI stays the same.

...
Test: ubuntu-20.04.clang.python39.rfd

 View log

Loading...

 View log in dialog  View log in log in separate window


branch: RFdiffusion:main 「№16」
Commited by: Hope Woods
GitHub commit link: 「ff20fbafefbdc9b9」
Difference from previous tested commit:  code diff
Commit date: 2025-11-13 16:33:05
rfd

Fix workflow tests that are failing (#410) This PR updates the tests so that all the examples run and if an example fails then the test results in a failure as well. Changes include: - Reformatting design_macrocyclic_binder.sh and design_macrocyclic_monomer.sh to be submitted correctly by test_diffusion.py - Reducing the total length in design_tetrahedral_oligos.sh to reduce run time of this test - Changes to test_diffusion.py and main.yml to be able to run the examples in different chunks so examples can run in parallel and to make sure that if an example errors out, that the tests does not pass. Currently design_ppi_scaffolded, design_timbarrel, and design_ppi_flexible_peptide_with_secondarystructure_specification are failing which should be addressed in other, future PRs.

...
Test: ubuntu-20.04.clang.python39.rfd

 View log

Loading...

 View log in dialog  View log in log in separate window


branch: RFdiffusion:main 「№15」
Commited by: Hope Woods
GitHub commit link: 「e22092420281c644」
Difference from previous tested commit:  code diff
Commit date: 2025-09-24 10:28:03
rfd

Retain chain and residue numbering in RFdiffusion (#348) A number of issues (e.g., #103 , #171 , https://github.com/RosettaCommons/RFdiffusion/issues/312 , #315 ) have mentioned that RFdiffusion will change the chain IDs and residue numbering of the input structure. The designed chain ends up as chain "A", and the fixed chain(s) end up as chain "B". The numbering is also reset to start at 1. This can be particularly problematic in cases where comparisons to structures are needed, as well as multi-chain situations where all of the chains get fused. Inspired by @GCS-ZHN 's comment and solution referenced in Issue #103 , I've modified the code to maintain chain and residue numbering. In particular: Chains that are not "designable" will retain their original chain ID letters and residue numbers. Chains that are partially fixed (e.g., motif re-scaffolding) will retain their original chain ID letters. Residues will be re-numbered from 1 to length of chain. (It was not clear to me what the "correct" behaviour of chain residue numbering should be, given that the length of the chain and the position of any fixed residues might change.) Chains that are being fully generated de novo will be assigned the first available chain ID in the alphabet not used by any other chain. Residues will be numbered from 1 to length of chain.

...
Test: ubuntu-20.04.clang.python39.rfd

 View log

Loading...

 View log in dialog  View log in log in separate window


branch: RFdiffusion:main 「№14」
Commited by: Hope Woods
GitHub commit link: 「735de5edb1adce7e」
Difference from previous tested commit:  code diff
Commit date: 2025-09-23 12:38:58
rfd

Update README.md (#365) Update README to point to new [documentation resource](https://sites.google.com/omsf.io/rfdiffusion/overview). I also added some text in the Installation section to 1) specify that Sergey O.'s colab notebook only contains some of the features of RFdiffusion and 2) that there is now a Rosetta Commons-maintained docker image.

...
Test: ubuntu-20.04.clang.python39.rfd

 View log

Loading...

 View log in dialog  View log in log in separate window


branch: RFdiffusion:main 「№13」
Commited by: Sergey Lyskov
GitHub commit link: 「fa340147b9006156」
Difference from previous tested commit:  code diff
Commit date: 2025-06-23 14:49:31
rfd

add GitHub CI workflow for running ppi-scaffolds tests (#1)

...
Test: ubuntu-20.04.clang.python39.rfd

 View log

Loading...

 View log in dialog  View log in log in separate window


branch: RFdiffusion:main 「№12」
Commited by: David Juergens
GitHub commit link: 「b254828f0774ecca」
Difference from previous tested commit:  code diff
Commit date: 2025-06-22 20:56:19
rfd

Update README.md

...
Test: ubuntu-20.04.clang.python39.rfd

 View log

Loading...

 View log in dialog  View log in log in separate window


branch: RFdiffusion:main 「№11」
Commited by: Joseph Watson
GitHub commit link: 「b44206a2a79f219b」
Difference from previous tested commit:  code diff
Commit date: 2024-08-26 13:35:40
rfd

correct example

...
Test: ubuntu-20.04.clang.python39.rfd

 View log

Loading...

 View log in dialog  View log in log in separate window


branch: RFdiffusion:main 「№10」
Commited by: Joseph Watson/Watchwell
GitHub commit link: 「820bfdfaded8c260」
Difference from previous tested commit:  code diff
Commit date: 2023-10-03 17:31:36
rfd

Update LICENSE

...


branch: RFdiffusion:main 「№9」
Commited by: Joseph Watson
GitHub commit link: 「46c0ef6803df475b」
Difference from previous tested commit:  code diff
Commit date: 2023-09-13 20:05:04
rfd

Implemented inpaint_str and added example

...


branch: RFdiffusion:main 「№8」
Commited by: Joseph Watson
GitHub commit link: 「ba8446eae0fb80c1」
Difference from previous tested commit:  code diff
Commit date: 2023-07-25 13:47:14
rfd

Added input pdb for p53 case

...


branch: RFdiffusion:main 「№7」
Commited by: Javier Castellanos
GitHub commit link: 「9149e5395a33e8b3」
Difference from previous tested commit:  code diff
Commit date: 2023-07-25 13:16:40
rfd

Fixed incorrect variable name in contig parsing

...


branch: RFdiffusion:main 「№6」
Commited by: Sergey Lyskov
GitHub commit link: 「5606075d45bd23aa」
Difference from previous tested commit:  code diff
Commit date: 2023-06-28 11:59:51

updating rosetta-ci test script, adding unpacking ppi scaffolds

...


branch: RFdiffusion:main 「№5」
Commited by: Rocco Moretti
GitHub commit link: 「9da13dc5b37eb2eb」
Difference from previous tested commit:  code diff
Commit date: 2023-06-27 11:38:38

Update install instructions for model directory location. Be more specific about the location of the models directory. Addresses issue #80

...


branch: RFdiffusion:main 「№4」
Commited by: Nick Randolph
GitHub commit link: 「b4f4c264a7256ae8」
Difference from previous tested commit:  code diff
Commit date: 2023-06-22 13:03:14

Fixed model_only_neighbors typo

...


1 2 >

Legend:
queued Queued Test
queued for comparison Test finished running but not yet compared
running Test is Running right now
comparing Test results is now comparing with previous results
finished Test is finished without errors
failed Test failed
build Failed Test could not be run because build failed
script failed Test results is unknow because test-script failed
canceled Test was canceled