Get the latest tech news

UCCL-EP: DeepEP-style expert parallelism on any NIC, no GPU-initiated comms

How UCCL reimplements the DeepEP kernels for arbitrary hardware by swapping the transport out from under them.

None

Related news:

Building a Korean ambiguity solver fast enough to skip the GPU: 7,300 words/SEC

NVIDIA challenger D-Matrix claims AI chip 10 times faster than GPU using 5 times less energy, skips DRAM for SRAM

Intel's mysterious new datacenter GPU is what Nvidia's Rubin CPX nearly was