HyPAIC: Personal AI Computer with High Bandwidth Flash for High Performance Trillion-Parameter LLM Inference
cs.AR
Submitted: 2026-11-03
Updated: 2026-11-03
Comments: 14 pages, 16 figures, 4 tables
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- Fate: Fast Edge Inference of Mixture-of-Experts Models via Cross-Layer Gate
- HAVEN: High-Bandwidth Flash Augmented Vector Engine for Large-Scale Approximate Nearest-Neighbor Search Acceleration
- Kimi K2.5: Visual Agentic Intelligence
- Incompressible Knowledge Probes: Estimating Black-Box LLM Parameter Counts via Factual Capacity
- Chakra: Advancing Performance Benchmarking and Co-design using Standardized Execution Traces
- ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference
- FlashAccel: Leveraging High-Bandwidth Flash for High-Throughput LLM Inference
- MemExplorer: Navigating the Heterogeneous Memory Design Space for Agentic Inference NPUs
- AIConfigurator: Lightning-Fast Configuration Optimization for Multi-Framework LLM Serving
- Pre-Attention Expert Prediction and Prefetching for Mixture-of-Experts Large Language Models
Related papers
- Embedded Arena: Iterative Optimization via Hardware Feedback
- WitCert: Sound Runtime Risk Observability and Gating for KV-Cache Quantization
- SparsePixels: Efficient Convolution for Sparse Data on FPGAs
- Golden Ruler: A Numeric Format Catalog with Bit-Exact Conformance Vectors for FP8, BF16, MXFP4, and Microscaling Formats
- AMMA: A Multi-Chiplet Memory-Centric Architecture for Low-Latency 1M Context Attention Serving
- RFChipAgent: Multi-Agentic AI Flow for Analog/RF Chip Design