9 Commits (main)

Author SHA1 Message Date
Edenzzzz 2a25a2aff7
[Feature] optimize PP overlap (#5735) 5 months ago
Hongxin Liu 7f8b16635b
[misc] refactor launch API and tensor constructor (#5666) 7 months ago
Hongxin Liu d202cc28c0
[npu] change device to accelerator api (#5239) 11 months ago
Elsa Granger d565df3821
[pipeline] A more general _communicate in p2p (#5062) 11 months ago
Wenhao Chen d799a3088f
[pipeline]: add p2p fallback order and fix interleaved pp deadlock (#5214) 11 months ago
Wenhao Chen 4fa689fca1
[pipeline]: fix p2p comm, add metadata cache and support llama interleaved pp (#5134) 11 months ago
Hongxin Liu 079bf3cb26
[misc] update pre-commit and run all files (#4752) 1 year ago
Hongxin Liu 45fdc9b42c [pipeline] implement p2p communication (#4100) 1 year ago