We have 3 of 4 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
HoliBench is presented, a modular benchmarking and deployment toolkit that jointly characterizes accuracy, latency, and energy across platforms from single-board computers to GPU servers and is released as open-source infrastructure for deployment-aware evaluation of foundation models.
This work frames 4-bit KV caching around multi-round agent workloads where task quality, cache residency, and serving throughput must be measured jointly, and presents serving optimizations on AMD GPUs, including optimized decode-attention kernels and UltraQuant.
LorExperts is introduced, a router-preserving compression method that clusters experts, keeps one full-precision dominant per cluster, and represents the remaining members as low-rank corrections to their local dominant, and BTExperts is introduced, a tree organization of dominants and corrections that enables inferenc...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
