Resources
  • Whitepapers, aiDAPTIV™Technology

What is aiDAPTIV

Altogether, fine-tuning has high GPU memory requirements so model size, batch size, and context length are heavily dependent on how much GPU memory is available on a system, not the amount of compute power available. Phison’s Pascari aiDAPTIV technology aids these GPU memory limitations by adding cache memory to the mix.

Download

SEAMLESS INTEGRATION

  • Optimized middleware to extends GPU memory capacity
  • 2x 2TB aiDAPTIVCache to support 70B model
  • Low latency

HIGH ENDURANCE

  • Industry-leading 100 DWPD with 5-year warranty
  • SLC NAND with advanced NAND correction algorithm

aiDAPTIV+ BENEFITS

  • Transparent drop-in
  • No need to change your AI Application
  • Reuse existing HW or add nodes

aiDAPTIV+ MIDDLEWARE

  • Slice model, assign to each GPU
  • Hold pending slices on aiDAPTIVCache
  • Swap pending slices w/ finished slices on GPU

FOR SYSTEM INTEGRATORS

  • Access to ai100E SSD
  • Middleware library license

  • Full Phison support to bring up