9 Commits

Author SHA1 Message Date
903a931d36 Improve documentation on running data pipeline and inference separately
Prompted by https://github.com/google-deepmind/alphafold3/issues/485.

PiperOrigin-RevId: 789700619
Change-Id: I0e876a1130cc537421e8916fcad1230302196b64
2025-08-01 03:56:58 -07:00
537a9e1d16 Explain the pair_transition_shard_spec format
PiperOrigin-RevId: 715803444
2025-01-16 14:27:02 +00:00
781d8d04f9 Add XLA flag workaround for CUDA Capability 7.x GPUs
PiperOrigin-RevId: 705559274
2024-12-13 06:35:21 +00:00
e56abb7a55 Update advice for different devices
PiperOrigin-RevId: 700993687
2024-11-28 16:44:11 +00:00
b108eedc04 Add a table of H100 inference timings to docs/performance.md
PiperOrigin-RevId: 697644061
2024-11-18 16:53:42 +00:00
4b2b567103 Documentation updates - older GPUs and JAX installation
PiperOrigin-RevId: 697634146
2024-11-18 16:21:14 +00:00
2ffe43f574 Fix pallas GLU kernel on large inputs and update documentation for compilation buckets.
PiperOrigin-RevId: 696513320
2024-11-14 15:20:38 +00:00
0341fb7f24 Documentation fixes and silence irrelevant warning
PiperOrigin-RevId: 695740242
2024-11-12 16:24:34 +00:00
4f52a3bb62 Initial release of AlphaFold 3
PiperOrigin-RevId: 695257954
2024-11-11 10:42:47 +00:00