A derivation- and implementation-oriented study of exact KV offload, compute-near-data attention, hierarchical residency, query-dependent retrieval, recallable memory, consistency, fallback, and serving evaluation.
A derivation-, state-, scheduler-, and operations-level treatment of continuous-batch speculative decoding, adaptive draft budgets, goodput control, target and draft cache synchronization, evaluation, canary release, and rollback.
A byte-, tensor-, graph-, and kernel-level treatment of quantized deployment artifacts: safetensors, GGUF, ONNX QDQ/QOperator, packing and alignment, sharding, converter and loader state machines, topology-aware placement, kernel admission, parity ladders, startup memory, security, and runtime integration across vLLM, TorchAO, TensorRT-LLM, and llama.cpp.
A systems study of serving many LoRA adapters over one base model: heterogeneous batching, segmented kernels, paging, residency, merge and hotswap semantics, request/KV compatibility, scheduling, observability, and failure recovery.
A derivation- and implementation-oriented study of physical KV layout, PagedAttention, vAttention, exact prefix identity, RadixAttention, ownership, and execution reuse.