"Enabling Cost-Efficient LLM Inference on Mid-Tier GPUs With NMP DIMMs."

Heewoo Kim, Alan La, Joseph Izraelevitz (2026)

> Home

Details and statistics

DOI: 10.1109/LCA.2025.3646622

access: closed

type: Journal Article

metadata version: 2026-01-20

- view
  - electronic edition via DOI
  - unpaywalled version
  authority control:
- export record
  dblp key:
  - journals/cal/KimLI26
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/journals/cal/KimLI26
Heewoo Kim, Alan La, Joseph Izraelevitz:
Enabling Cost-Efficient LLM Inference on Mid-Tier GPUs With NMP DIMMs. IEEE Comput. Archit. Lett. 25(1): 21-24 (2026)

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.