Purpose-built kernel agents can write high-performance GPU kernels, but existing systems generally lack cross-run knowledge accumulation and architectural evolution. Each run starts from the same initial knowledge, and later iterations largely optimize within an architecture fixed early in the search. We present ForgeKernel, a kernel-generation system that accumulates and reuses knowledge across runs while enabling continued evolution of kernel architectures. It analyzes the hardware behavior of a high-performance reference and distills validated architectural decisions into reusable knowledge of hardware mechanisms rather than imitating source code. It then seals a kernel that passes correctness and performance validation and uses it as the reference for the next optimization run, enabling architectural decisions to be revisited. Across 27 operators and 29 input configurations on NVIDIA Hopper and Blackwell GPUs, ForgeKernel matches or beats its expert reference on 25 configurations, with a geometric-mean performance gain of 10%. On Ascend 910C, it outperforms the per-operator public best on the public case set of all 8 level-4 operators in the CANN-Bench Season 1 final leaderboard, with a geometric-mean gain of 25.1%, while its full-suite submission ranks first on the A3 leaderboard. As of 2026-10-30, public submissions generated by ForgeKernel rank first on all three CANN-Bench 2.0 solution leaderboards (Ascend 910C, 950DT, and 950PR) and on the SOL-ExecBench FlashInfer-Bench track.
Single-GPU deployment of 70B-parameter language models on an NVIDIA GPU is constrained by device memory, long-context throughput, and engineering integration cost. We cast single-GPU inference as a budget-aware design problem over these three axes and study how pruning, quantization, and KV-cache compression interact under realistic execution. Controlled ablations show that layer-wise pruning makes weight quantization more robust. KV-cache sparsification complements INT8 KV quantization by reducing memory without hurting decoding speed, while static vector quantizers often conflict with dynamic caching. Guided by these coupling results and explicit budget tracking, we assembled a practical pipeline and compressed a 70B model to about 33 GB, sustained about 57 tokens/s on 10k token prompts on a single A40, and kept absolute accuracy within 5% on common and reasoning benchmarks. We contribute design rules and a reproducible evaluation protocol that jointly report quality, memory, and end-to-end speed, and we provide a foundation for automated pipeline search under realistic single-GPU constraints.
A small number of GPU kernels often determines the efficiency of large language model training and inference. High-performance kernel development typically relies on expert knowledge through manual implementation, collaboration with general-purpose models, or specialized agents equipped with domain knowledge, evaluation methods, and search workflows. We investigate how much value this knowledge provides as foundation models become stronger. We introduce JustGoal, a goal-only baseline in which a general-purpose agent receives only the optimization objective and constraints, without kernel-specific infrastructure, knowledge bases, or predefined workflows, and builds its own evaluation loop. On NVIDIA B200 GPUs, JustGoal outperforms open-source libraries on 8 of 10 operators, achieving per-operator geometric mean speedups of 1.14x to 2.34x. It also surpasses the fastest publicly released specialized-agent kernel on 5 of 9 operators with available comparisons. In a controlled same-model comparison using Fable 5.1 on single shapes, the KDA-0.5 harness reaches 0.95x of JustGoal's performance, while single-mechanism ablations show no consistent benefit from domain knowledge or predefined workflows. These results indicate that specialized machinery should be justified by clear gains over a same-model, same-scope goal-only baseline and reevaluated whenever the foundation model changes.
Justice Ou University of Illinois at Urbana-Champaign, Tinglin Huang, Yilun Zhao Yale University, Ziyang Yu, Peiqing Lu Microsoft, Yifei Shen, Rex Ying Yale University
To improve the reliability of Large Language Models (LLMs) in clinical applications, retrieval-augmented generation (RAG) is extensively applied to provide factual medical knowledge. However, beyond general medical knowledge from open-ended datasets, clinical case-based knowledge is also critical for effective medical reasoning, as it provides context grounded in real-world patient experiences. Motivated by this, we propose Experience Retrieval-Augmentation ExpRAG framework based on Electronic Health Record(EHR), aiming to offer the relevant context from other patients’ discharge reports. ExpRAG performs retrieval through a coarse-to-fine process, utilizing an EHR-based report ranker to efficiently identify similar patients, followed by an experience retriever to extract task-relevant content for enhanced medical reasoning. To evaluate ExpRAG, we introduce DischargeQA, a clinical QA dataset with 1,280 discharge-related questions across diagnosis, medication, and instruction tasks. Each problem is generated using EHR data to ensure realistic and challenging scenarios. Experimental results demonstrate that ExpRAG consistently outperforms a text-based ranker, achieving an average relative improvement of 5.2%, highlighting the importance of case-based knowledge for medical reasoning.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表