Enter your email above, then click "Sign Up" to join the STAC mail list and (optionally) register to access materials on the site. Click for terms.
A comparison between self-hosted LLMs and API services
Under STAC-T0, max actionable latency of 44 nanoseconds across all message sizes and rates
2.67x the space efficiency and 1.25x the energy efficiency of a system using the single-chip Cascade Lake
NFS-based solution beats previously tested Lustre-based solution in most benchmarks
Solution sets 8 records in scale tests
6,250 times as many simulations on a basket of 50 instruments in 1 hour as the previous record
Cascade Lake solution computed Greeks 23-84% faster than Skylake solution
First STAC-M3 results on Microsoft Azure
Read the latest about research, events, and other important news from STAC.
