# deepseek-ai/TileKernels

A kernel library written in tilelang

Repository: https://github.com/deepseek-ai/TileKernels
Canonical: https://ross.abutalabs.com/products/tilekernels
Language: Python
License: MIT
License Family: permissive
Last push: 2026-04-23T10:19:21+00:00

## Health v2 (maintenance only)
Score: 49/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 78, release rhythm 35, longevity 9
- inputs: {"age_days": 133, "days_push": 132, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1743, forks 160 (observed 2026-08-28T04:05:30.445569+00:00)

## What it is
TileKernels is a Python library of optimized GPU kernels for LLM operations, written in the TileLang DSL. It provides kernels for MoE routing, FP8/FP4 quantization, batched transpose, and engram/hyper-connection operations, with high-level torch.autograd wrappers for training.

## Use cases
- speed up mixture of experts routing on nvidia gpus
- fp8 and fp4 quantization kernels for llm training
- fused swiglu quantization ops
- custom gpu kernels written in tilelang
- engram gating kernels with rmsnorm fusion
- benchmark gpu kernels near hardware limits

## When to choose
- you need near-hardware-limit GPU kernels for MoE or quantization on SM90/SM100
- you already use TileLang and want reusable LLM kernels
- you want autograd-compatible layers for custom LLM ops

## When to avoid
- you need portable kernels across AMD or older NVIDIA GPUs
- you want a production-ready, well-documented library
- you don't use PyTorch 2.10+ or CUDA 13.1+

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, gpu-computing, llm-training, llm-inference, benchmarking
- domain: deep-learning, large-language-models, gpu-computing, developer-tools
- platform: python
- tags: tilelang, gpu-kernels, mixture-of-experts, fp8, fp4, quantization, cuda, nvidia, deepseek, gpu, linux

## Member repositories
- deepseek-ai/TileKernels (main) score 49

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:30.445569+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:29:32.673911+00:00, confidence not recorded.
  - readme: https://github.com/deepseek-ai/TileKernels (fetched 2026-08-28T04:05:30.445569+00:00, sha d1706aa357c0)
- Data as of 2026-08-30T08:39:29.467469+00:00.