Learn how vLLM and llm-d work together for efficient and scalable large language model (LLM) inference. Discover the benefits of disaggregated scaling, expert-parallel scheduling, and KV cache-aware routing.
vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
LLM in a Flash: Efficient Large Language Model Inference with Limited Memory
Large language models (LLMs) are central to modern natural language processing, delivering exceptional performance in various tasks…
An Internet for the KV Cache: Rethinking Classical Infrastructure Boundaries in the LLM Inference Age
LLM inference has become a global-scale, heterogeneous workload spanning agents, retrieval, tool-use, code execution and multi-modal reasoning. These workloads naturally enable context reuse from overlapping inputs, creating a major opportunity to store and reuse the contexts' KV Caches instead of recomputing them. However, model-side advances that shrink the KV Cache and system-side advances that reduce compute, storage, and transfer costs are evolve independently within legacy cloud boundaries. We argue that future inference infrastructure should allow decoupling of compute and KV Cache storage across cloud and datacenters. The network becomes an active distribution channel; bandwidth, latency and pricing directly determines how the KV Cache should be managed. We propose a vision for an Internet for the KV Cache, with KV Cache management working as a content-distribution system. In this view, KV Cache storage and recompute decisions are driven by model, infrastructure, and application metrics, to enable adaptive, content-driven decisions for minimizing latency and cost.
vLLM Semantic Router: Next Phase in LLM inference
How vLLM Semantic Router routes requests by intent, covering semantic classification, smart reasoning-path selection, Rust and Candle execution, and Kubernetes
Wolfram LLM Benchmarking Project
Results from Wolfram's ongoing tracking of LLM performance. The benchmark is based on a Wolfram Language code generation task.
Scaling Laws Across Model Architectures: A Comparative Analysis of...
The scaling of large language models (LLMs) is a critical research area for the efficiency and effectiveness of model training and deployment. Our work investigates the transferability and...
On-Device LLM Throughput Calculator - a Hugging Face Space by FL33TW00D-HF
This tool estimates and visualizes the throughput of Large Language Models on devices with memory bandwidth constraints. Users input device and model configurations, and the tool generates a plot s...
LLM in a flash: Efficient Large Language Model Inference with Limited Memory
Large language models (LLMs) are central to modern natural language processing, delivering exceptional performance in various tasks. However, their substantial computational and memory requirements present challenges, especially for devices with limited DRAM capacity. This paper tackles the challenge of efficiently running LLMs that exceed the available DRAM capacity by storing the model parameters in flash memory, but bringing them on demand to DRAM. Our method involves constructing an inference cost model that takes into account the characteristics of flash memory, guiding us to optimize in two critical areas: reducing the volume of data transferred from flash and reading data in larger, more contiguous chunks. Within this hardware-informed framework, we introduce two principal techniques. First, "windowing" strategically reduces data transfer by reusing previously activated neurons, and second, "row-column bundling", tailored to the sequential data access strengths of flash memory, increases the size of data chunks read from flash memory. These methods collectively enable running models up to twice the size of the available DRAM, with a 4-5x and 20-25x increase in inference speed compared to naive loading approaches in CPU and GPU, respectively. Our integration of sparsity awareness, context-adaptive loading, and a hardware-oriented design paves the way for effective inference of LLMs on devices with limited memory.
How To Scale Your Model
Training LLMs often feels like alchemy, but understanding and optimizing the performance of your models doesn't have to. This book aims to demystify the science of scaling language models: how TPUs (and GPUs) work and how they communicate with each other, how LLMs run on real hardware, and how to parallelize your models during training and inference so they run efficiently at massive scale. If you've ever wondered “how expensive should this LLM be to train” or “how much memory do I need to serve this model myself” or “what's an AllGather”, we hope this will be useful to you.
Beyond Model Collapse: Scaling Up with Synthesized Data Requires...
Large Language Models (LLM) are increasingly trained on data generated by other LLM, either because generated text and images become part of the pre-training corpus, or because synthetized data is...
ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities
Recent large language models (LLMs) advancements sparked a growing research interest in tool assisted LLMs solving real-world challenges…
Large language model
A large language model (LLM) is a neural network trained on a vast amount of text for natural language processing tasks, especially language generation. LLMs can typically generate, summarize, translate, and analyze text in many contexts, and are a foundational technology behind modern chatbots.[1] Biased or inaccurate training data can make an LLM's output less reliable.[2]
Intelligence per Watt: Measuring Intelligence Efficiency of Local AI
Large language model (LLM) queries are predominantly processed by frontier models in centralized cloud infrastructure. Demand growth strains this paradigm faster than providers can scale. Two advances create an opportunity to rethink it: small, local LMs (<=20B active parameters) now achieve competitive performance to frontier models on many tasks, and local accelerators (e.g., Apple M4 Max) can host these models at interactive latencies. This raises the question: can local inference viably redistribute demand from centralized infrastructure? This requires measuring both whether local LMs can accurately answer real-world queries and whether they can do so efficiently on power-constrained devices (e.g., laptops). We propose intelligence per watt (IPW), task accuracy per unit of power, as a unified metric for the capability and efficiency of local inference across model-accelerator configurations. We evaluate 20+ state-of-the-art local LMs, 8 hardware accelerators (local and cloud), and 1M real-world single-turn chat and reasoning queries. For each query, we measure accuracy (local LM win rate against frontier models), energy, latency, and power. We find three key results. First, local LMs successfully answer 88.7% of these queries, with accuracy varying by domain. Second, longitudinal analysis from 2023-2025 shows IPW improved 5.3x, driven by both algorithmic and accelerator advances, with locally-serviceable query coverage rising from 23.2% to 71.3%. Third, local accelerators achieve at least 1.4x lower IPW than cloud accelerators running identical models, revealing significant headroom for local accelerator optimization. These findings demonstrate that local inference can meaningfully redistribute demand from centralized infrastructure for a substantial subset of queries, with IPW serving as the critical metric for tracking this transition.
The Case Against LLMs as Rerankers
Authors: Apoorva Joshi, Zhenmei Shi, Akshay Goindani, Hong LiuResearch Leads: Zhenmei Shi, Akshay Goindani, Hong Liu Large language models are increasingly being used for a broad range of tasks, in…
Infinite-Parameter LLMs: Generating and Adapting Weights from Live Data
Scaling laws hold that language models grow more capable with more parameters and more training data. Mixture-of-Experts (MoE) architectures are a remarkable demonstration of these laws, activating only a fraction of an enormous parameter bank for each token. But this success is built on static pretraining data --- the facts and corrections supplied by users during live interactions are a significant untapped source of potential improvement for a deployed model, but cannot be exploited by conventional architectures whose weights are frozen after training. Instead, this newfound knowledge must be placed in the context (by instruction or retrieval) and re-read on every request, only to be discarded afterwards. We seek instead to learn from live interactions by dynamically updating model weights. Inspired by MoEs, we propose the \textbf{Infinite-Parameter LLM}. A compact hypernetwork turns the online data into low-rank modulations of a shared base network, so feed-forward weights are generated from live data, not read from static memory. Whereas existing weight generators are held fixed after reading the context once, we form a Bayesian belief over the generator's latent state and update it online, such that the effective weights are re-derived as our belief evolves during the session. Although the model's memory footprint is constant, the feasible space of generated weights is thus effectively infinite. Representing live data in the weights rather than the prompt amortises compute, frees the context window, persists updates across turns, and can generalise better than in-context use. Our evaluation protocol applies this methodology to in-context learning and retrieval.