arXiv:2402.07033 - Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models
paper
Fields
id
sources/pap-w4p-fiddlerPublisher
arXiv
Kind
paper
Published
2024-02-10
Accessed
2026-10-04
notes
arXiv:2402.07033, v1 2024-02-10, latest v3 2025-05-01. arXiv comment reads 'ICLR2025'; confirmed by the OpenReview decision record 'ICLR 2025 Poster' (forum N5fVv6PZGz, venueid ICLR.cc/2025/Conference) AND a separate DBLP-mirrored note crossref conf/iclr/2025. Note the arXiv v1 author list is 4 authors (Kamahori, Gu, Zhu, Kasikci) and later versions add Tian Tang - the OpenReview ICLR record carries 5 authors, which is why author overlap was used to confirm identity rather than a bare title match. Authors Keisuke Kamahori, Tian Tang, Yile Gu, Kan Zhu, Baris Kasikci.
Notes
arXiv:2402.07033, v1 2024-02-10, latest v3 2025-05-01. arXiv comment reads 'ICLR2025'; confirmed by the OpenReview decision record 'ICLR 2025 Poster' (forum N5fVv6PZGz, venueid ICLR.cc/2025/Conference) AND a separate DBLP-mirrored note crossref conf/iclr/2025. Note the arXiv v1 author list is 4 authors (Kamahori, Gu, Zhu, Kasikci) and later versions add Tian Tang - the OpenReview ICLR record carries 5 authors, which is why author overlap was used to confirm identity rather than a bare title match. Authors Keisuke Kamahori, Tian Tang, Yile Gu, Kan Zhu, Baris Kasikci.
Cross-references
This record references no other records.