datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
kernelbench-hard-traces
KernelBench-Hard agent traces
Frontier coding agents writing optimized CUDA/Triton kernels (FP8 GEMM, paged
attention, MoE, W4A16, KDA, Top-k) on RTX PRO 6000 Blackwell, H100 PCIe, and
B200; roofline-graded.
Each .jsonl file is one agent run in Claude-Code session format, viewable with
the Hugging Face Agent Trace viewer (Data Studio → open a row). Filename =
run id.
Live leaderboard: https://kernelbench.com/hard
Secrets redacted. Full reasoning for open-provider routes… See the full description on the dataset page: https://huggingface.co/datasets/Infatoshi/kernelbench-hard-traces.glm-5.2-kernelgym-rollouts
GLM-5.2 KernelGym Rollouts
This dataset contains 3,200 feedback-driven GPU-kernel optimization trajectories
generated by zai-org/GLM-5.2-FP8: 100 validation tasks, two backends (inline
CUDA and Triton), and 16 rollouts per task.
Each trajectory retains the prompt/feedback message history, model responses and
reasoning, extracted kernel code, KernelGym compilation and correctness results,
profiling metadata, token usage, and stopping decision. Every published record
ended with… See the full description on the dataset page: https://huggingface.co/datasets/marin-community/glm-5.2-kernelgym-rollouts.autonomous-linux-kernel-ebpf-xdp-suite
⚡ Autonomous Linux Kernel, eBPF & XDP Programmable Dataplane Suite (2026)
A Production-Grade, Verifiable Synthetic Corpus for Training Autonomous Linux Kernel & eBPF Systems Agents
⚡ Overview & Industry Problem
Modern hyperscale cloud datacenters, bare-metal Kubernetes clusters, and low-latency financial trading nodes rely on in-kernel programmable dataplanes: eBPF, AF_XDP zero-copy rings, Traffic Control (TC) shapers, BPF LSM security hooks… See the full description on the dataset page: https://huggingface.co/datasets/beatsprom/autonomous-linux-kernel-ebpf-xdp-suite.autonomous-gpu-kernel-triton-cuda-suite-2026
⚡ Autonomous GPU Kernel, Triton & CUDA Architecture Suite (2026)
A Production-Grade, Verifiable Synthetic Corpus for Training Frontier Coding Models (Qwen 3.8, DeepSeek-V3, Llama 3.3)
⚡ Overview & Industry Problem
Modern deep learning accelerators, custom ASICs, and high-performance computing clusters demand specialized, autonomous GPU kernel infrastructure: OpenAI Triton fused kernels, FlashAttention-3 forward/backward online softmax… See the full description on the dataset page: https://huggingface.co/datasets/beatsprom/autonomous-gpu-kernel-triton-cuda-suite-2026.cuda-triton-gpu-kernels-2026
⚡ Complete 2026 CUDA & OpenAI Triton High-Performance GPU Kernel Engineering SFT/DPO Suite
The definitive, production-grade synthetic alignment dataset engineered for training and fine-tuning open-weights Large Language Models (Qwen 2.5 Coder, DeepSeek-Coder, Llama 3.1) on ultra-high-throughput GPU kernel programming: NVIDIA Hopper H100 / Blackwell B200 TMA async transfers, OpenAI Triton 3.1+ FlashAttention-3, 32-bank conflict elimination, and low-bit FP8 / INT4 GEMM… See the full description on the dataset page: https://huggingface.co/datasets/beatsprom/cuda-triton-gpu-kernels-2026.deepseek-r1-systems-kernel-reasoning
🧠 DeepSeek-R1 Low-Level Systems & Kernel Reasoning Suite (2026)
🛒 Commercial Full Suite Available:
The full production suite with 10,000 SFT Hardware Reasoning Traces + 2,500 High-Contrast DPO Alignment Pairs across all 20 domains is available on Gumroad:
👉 Download Full Commercial Dataset on Gumroad (Starter \ / Pro \ / Enterprise )
A Tier-1 Commercial Dataset Suite engineered specifically for fine-tuning DeepSeek-R1, DeepSeek-R1-Distill-Qwen-14B/32B, and frontier… See the full description on the dataset page: https://huggingface.co/datasets/beatsprom/deepseek-r1-systems-kernel-reasoning.KernelBenchX
KernelBenchX
Reproducible evaluation benchmark for Triton GPU-kernel code generation by LLMs — measures buildability, numerical correctness against a deterministic test suite, and end-to-end speedup vs. a GPU-matched golden reference.
Paper: arXiv:2605.04956 · hf.co/papers/2605.04956
Evaluation harness: https://github.com/BonnieW05/KernelBenchX
Configs
Config
Rows
What it is
tasks
176
Benchmark task specs + PyTorch reference + deterministic test harness… See the full description on the dataset page: https://huggingface.co/datasets/BonnieWang/KernelBenchX.ParallelKernelBench_Kernels
ParallelKernelBench Kernels
Net-new multi-GPU CUDA kernels generated by LLMs for ParallelKernelBench.
Each subdirectory under solutions/ is one model run. File names match the benchmark problem stems (e.g. 17_rope_allgather_cuda.py ↔ problem 17_rope_allgather in willychan21/ParallelKernelBench_Problems).
Layout
solutions/
<run_id>/
<stem>_cuda.py
...
Runs (1 run(s), 87 kernel files)
run_id
kernels
path… See the full description on the dataset page: https://huggingface.co/datasets/willychan21/ParallelKernelBench_Kernels.kernelbook-triton-reasoning-traces
KernelBench Triton Reasoning Traces
Reasoning traces generated by the gpt-oss-120b model for converting PyTorch modules to Triton GPU kernels.
Dataset Description
This dataset contains 170 reasoning traces around 85% of them are correct where a PyTorch module was successfully converted to a Triton kernel. Each sample includes the original PyTorch code, the model's reasoning process, and the resulting Triton kernel code along with correctness and performance benchmarks.… See the full description on the dataset page: https://huggingface.co/datasets/ppbhatt500/kernelbook-triton-reasoning-traces.kernelbook-opus4.8-multiturn-traces
KernelBook → Triton: Multi-Turn Generation Traces (Opus 4.8)
Multi-turn agentic traces of Claude Opus 4.8 converting PyTorch modules into
Triton GPU kernels. Each row is one problem from
GPUMODE/KernelBook: the model
writes a kernel, runs it on a GPU against the reference, reads the
correctness + speedup feedback, and iterates — so every trace is a grounded,
tool-using optimization loop, not a single-shot completion.
How it was generated
Model: claude-opus-4-8… See the full description on the dataset page: https://huggingface.co/datasets/ppbhatt500/kernelbook-opus4.8-multiturn-traces.