arXiv:2607. 14431v1 Announce Type: cross Abstract: We report a way to make a frozen small language model both more capable and dramatically cheaper at once, without changing any weights.
arXiv:2607. 23806v1 Announce Type: cross Abstract: Improving a language model today means retraining it: enormous compute, a new opaque model each cycle, non-deterministic output.
arXiv:2607. 28495v1 Announce Type: new Abstract: Stage-replay diagnostics reconstruct intermediate token prefixes and treat fresh-prefill continuation as continuation from the decoder state that originally reached the prefix.
arXiv:2603. 09555v2 Announce Type: replace-cross Abstract: High-throughput Mamba-2 inference is usually tied to fused CUDA and Triton kernels, limiting portability across accelerator backends.
arXiv:2609.37887v1 Announce Type: new Abstract: Activation and key-value cache precision change what a quantized language model computes without altering its stored weights. Direct weight-code bounds...
arXiv:2608. 08081v1 Announce Type: cross Abstract: Large mixture-of-experts (MoE) language models with 26--120 billion parameters exceed the memory capacity of consumer devices through three simultaneous pressures: resident weight matrices, key-value (KV) cache state that grows linearly with context, and dozens of expert sublayers that must be paged on demand.
arXiv:2607. 14568v1 Announce Type: cross Abstract: A companion study ran a 35B mixture-of-experts model on a 2011 NVIDIA Tesla C2075 (Fermi, sm_20, 6GB) as a GPU-prefill/CPU-decode hybrid, because the 4-bit model did not fit in device memory (arXiv:2606.
arXiv:2607. 07144v1 Announce Type: new Abstract: The key-value (KV) cache dominates the memory cost of long-context autoregressive inference, and a growing body of work compresses it through quantization, eviction, or offloading.
arXiv:2609.36654v1 Announce Type: new Abstract: Large language models make weight storage and memory traffic major inference costs, motivating low-precision formats that represent each weight with on...
The paper investigates whether training Mixture-of-Experts (MoE) routers can improve memory‑bandwidth locality on consumer GPUs. Using a new zero‑surgery telemetry tool, the authors measure that a large Qwen3‑235B model is bottlenecked by disk‑based expert access, and that an LRU cache can serve a majority of requests. They pre‑register experiments training 137 M‑parameter MoE models with locality‑aware losses, finding that while cache misses can drop up to 60 % (99 % static‑pin hit rate), every configuration fails to meet a strict 1 % perplexity threshold, indicating a tight coupling between cache efficiency and model quality.
arXiv:2607. 22785v1 Announce Type: cross Abstract: Apple-Silicon SoCs share CPU, GPU, and Neural Engine over one unified memory system, raising the question of whether transformer inference can be accelerated by splitting single operators across units.
arXiv:2608. 08910v1 Announce Type: cross Abstract: PTQTP decomposes LLM weight matrices into two ternary (trit) planes with two free per-group scales.
arXiv:2609.14507v1 Announce Type: cross Abstract: Single-GPU long-context inference with Mixture-of-Experts (MoE) models requires spilling the key-value cache (KVCache) to CPU memory. The spilled KV...