arXiv AI
Jul 7
Fine-Grained Computation Offload for Off-the-Shelf Servers in Tens of Lines
arXiv:2607. 02630v1 Announce Type: cross Abstract: Hardware accelerators now sit on the critical path of online serving.
Elastic Gang: Per-Token Membership Change for a Hard-Barriered LLM Inference Gang Co-Scheduled with OS Processes
arXiv:2607. 04668v1 Announce Type: cross Abstract: On-device LLM decoding is a hard-barriered CPU-SIMD computation that wants every core for milliseconds per token, while the rest of the OS wants those same cores continuously.
Related stories
arXiv AI
Aug 14
TEMPO: Makespan-Aware Expert-Parallel Load Balancing Across Memory- and Compute-Bound Regimes
arXiv:2608. 13057v1 Announce Type: cross Abstract: In expert-parallel (EP) MoE serving, every layer synchronizes at the slowest GPU.
arXiv AI
Aug 26
Elastic KV Cache for LLM Serving:A Working Reclamation Mechanism, and Why Chunked Prefill Already Closes the Gap
The paper introduces an elastic key‑value (KV) cache for large language model (LLM) serving that dynamically reclaims a pre‑allocated reserve during decode‑heavy phases and restores it before prefill, using a userspace CUDA virtual‑memory trick that requires no driver changes. The authors implement this mechanism, test it under realistic workloads, and find that it offers only marginal benefits—about a 1 % difference in time‑to‑first‑token for large prefill chunks—and that simpler strategies such as lowering the maximum batch size can achieve similar results. The study also notes that the reserve’s impact diminishes with higher tensor‑parallelism levels. whyItMatters":"The work demonstrates that a dynamic KV cache reclamation strategy can be implemented without driver patches and that its practical benefits are limited, guiding future LLM serving optimizations toward simpler approaches."
arXiv Machine Learning
Sep 22
PAGE: Partition-Aware Gated KV-Cache Eviction
PAGE is a partition‑aware gated KV‑cache eviction method that reframes eviction as a per‑input admission decision. It uses a single label‑free scalar— the early‑to‑late drop in pairwise top‑k head agreement—to classify inputs into a capacity‑bound class (where eviction is catastrophic) and a dilution‑prone class (where eviction is safe or beneficial). By thresholding this drop, PAGE applies a base evictor only when necessary, reducing the harm rate in the capacity‑bound regime from 0.75 to 0.026 and achieving a 29× improvement across four models and benchmarks without retraining the evictor.
arXiv Machine Learning
Jul 28
FusionML: Prefill, Not Decode - Mechanism and Boundaries of CPU+GPU Co-Execution on Unified-Memory Apple Silicon
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 Machine Learning
Jul 7
Sangam: Efficiently Serving Diffusion LLMs with the AR Stack
arXiv:2607. 04206v1 Announce Type: cross Abstract: Diffusion language models (dLLMs) generate text by iteratively denoising a masked response and can commit multiple output positions per model invocation.
arXiv AI
Sep 1
PowerSlider: Exploiting Phase Asymmetry for LLM Serving under Demand Response
arXiv:2608.21719v1 Announce Type: cross Abstract: AI inference clusters are increasingly constrained by instantaneous power, not just energy: grid operators condition new capacity on demand response,...
arXiv AI
Aug 20
Cacheable by Design? Training Mixture-of-Experts Routers for Locality Against the Edge Memory-Bandwidth Wall: A Pre-Registered Negative Result with a Systems Measurement Study
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 Computation and Language
Sep 22
this-that-model-1.0: A typed decision model that decides in 30 ms, for a millionth of a cent
arXiv:2609.23886v1 Announce Type: new Abstract: Software delegates more of its branches to models every year: which queue a ticket enters, whether a command is safe to run, whether a claim clears wit...
Hugging Face Trending Papers
Jul 5
Sangam: Efficiently Serving Diffusion LLMs with the AR Stack
Diffusion language models (dLLMs) generate text by iteratively denoising a masked response and can commit multiple output positions per model invocation. Their bidirectional attention prevents exact autoregressive-style KV caching, since committing one position shifts the KV activations of all others.
arXiv AI
Jul 10
SMetric: Rethink LLM Scheduling for Serving Agents with Balanced Session-centric Scheduling
arXiv:2607. 08565v1 Announce Type: cross Abstract: LLM scheduling is critical to serving, yet it remains unclear how well existing designs fit agentic serving--with LLM requests issued by agents instead of humans.
arXiv Machine Learning
Sep 1
Ceiling-Clipped Acceptance Histograms Indicate Stranded Speed-up in Block-Diffusion Speculative Decoding
arXiv:2608.30427v1 Announce Type: cross Abstract: Speculative decoding speeds up generation with an efficient draft model (drafter) that proposes tokens for a target model to verify in one pass, pres...