Protein embedding still needs 1TB of memory and 384 CPU nodes for a single run
ebetica · x · 2026-07-22
A complaint about a protein-embedding workflow that still needs enormous resources: 1 TB of memory and 384 CPU nodes just to embed a single protein in about 10 minutes.
The point is less about one specific model than the operational absurdity of the current setup: even a single inference job can require a very large cluster footprint, which is a useful signal about the compute cost of large-scale bio/ML pipelines.
More from Infra
- Oracle Q1: Triple-digit cloud infrastructure growth as AI demand booms — DavidLinthicum · 2026-09-11
- SF Compute founder: buying compute is 'an absolutely awful experience' right now — IgorCarron · 2026-09-11
- SmolVM open-sources persistent computer infrastructure for agents that outlive chat sessions — aniketmaurya · 2026-09-11
- PyTorch Day Korea 2026 launches first offline conf, CFP closes Sept 13 — PyTorch · 2026-09-11
- Local LLM server dilemma: 4x CMP-170HX (price up 53% in 20 days) vs Mac Studio M5 Ultra — rumboll · 2026-09-11
- llama.cpp lands Flash Attention tuning for RDNA4, big prefill gains on AMD — pmttyji · 2026-09-11