FACT is a three-stage agent-driven system that synthesizes and composes CUTLASS kernels from PyTorch modules, achieving up to 2.03x speedup on transformer blocks over PyTorch and competing optimizers.
Ker- nelBlaster: Continual cross-task CUDA optimization via memory- augmented in-context reinforcement learning.CoRR, abs/2602.14293
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
years
2026 8representative citing papers
Hawk raises NPU kernel generation accuracy from 49.4% to 80% and yields up to 2.2× speedups by retrieving and distilling structured hardware-aware knowledge without any model training.
SpecGen introduces speculative generation to fork non-reasoning kernel candidates during LLM reasoning traces, enabling early termination and parallel profiling to reduce end-to-end optimization time on H200 GPUs.
KForge uses dual LLM agents for cross-platform kernel generation, reporting 2.12% throughput gain on NVIDIA B200 vs TensorRT-LLM and 5.13x geometric mean speedup on Intel Arc B580 vs PyTorch on 37 workloads.
KLineage derives verified optimization skills from backward lineages of expert GPU kernels to guide LLM agents toward higher-quality and more efficient kernels than memory-based baselines.
Argus generates GPU kernels achieving 99-104% of hand-optimized throughput on key LLM kernels by enforcing compile-time data-flow invariants via a tag-based DSL and an in-context RL planner.
HTAM builds a Hierarchical Transition Graph to organize coarse global directions and detailed local strategies for guiding LLM-based CUDA kernel optimization, improving results on KernelBench.
citing papers explorer
-
FACT: Compositional Kernel Synthesis with a Three-Stage Agentic Workflow
FACT is a three-stage agent-driven system that synthesizes and composes CUTLASS kernels from PyTorch modules, achieving up to 2.03x speedup on transformer blocks over PyTorch and competing optimizers.
-
Hawk: Harnessing Hardware-Aware Knowledge for High-Performance NPU Kernel Generation
Hawk raises NPU kernel generation accuracy from 49.4% to 80% and yields up to 2.2× speedups by retrieving and distilling structured hardware-aware knowledge without any model training.
-
SpecGen: Accelerating Agentic Kernel Optimization with Speculative Generation
SpecGen introduces speculative generation to fork non-reasoning kernel candidates during LLM reasoning traces, enabling early termination and parallel profiling to reduce end-to-end optimization time on H200 GPUs.
-
KForge: LLM-Driven Cross-Platform Kernel Generation for AI Accelerators
KForge uses dual LLM agents for cross-platform kernel generation, reporting 2.12% throughput gain on NVIDIA B200 vs TensorRT-LLM and 5.13x geometric mean speedup on Intel Arc B580 vs PyTorch on 37 workloads.
-
Learning When to Optimize: Verified Optimization Skills from Expert GPU-Kernel Lineages
KLineage derives verified optimization skills from backward lineages of expert GPU kernels to guide LLM agents toward higher-quality and more efficient kernels than memory-based baselines.
-
ARGUS: Agentic GPU Optimization Guided by Data-Flow Invariants
Argus generates GPU kernels achieving 99-104% of hand-optimized throughput on key LLM kernels by enforcing compile-time data-flow invariants via a tag-based DSL and an in-context RL planner.
-
HTAM: Hierarchical Transition-Attended Memory for Operator Optimization
HTAM builds a Hierarchical Transition Graph to organize coarse global directions and detailed local strategies for guiding LLM-based CUDA kernel optimization, improving results on KernelBench.
- Optimizing CUDA like a Human: Micro-Profiling Tools as Expert Surrogates for LLM-Based GPU Kernel Optimization