huggingface / kernel-builderLinks
π· Build compute kernels
β106Updated last week
Alternatives and similar repositories for kernel-builder
Users that are interested in kernel-builder are comparing it to the libraries listed below
Sorting:
- Load compute kernels from the Hubβ244Updated this week
- Collection of autoregressive model implementationβ86Updated 4 months ago
- Lightweight toolkit package to train and fine-tune 1.58bit Language modelsβ83Updated 3 months ago
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS β¦β61Updated 10 months ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clustersβ128Updated 8 months ago
- PCCL (Prime Collective Communications Library) implements fault tolerant collective communications over IPβ103Updated 2 weeks ago
- Storing long contexts in tiny caches with self-studyβ140Updated this week
- train with kittens!β62Updated 10 months ago
- PyTorch implementation of models from the Zamba2 series.β184Updated 7 months ago
- Train, tune, and infer Bamba modelβ131Updated 2 months ago
- An efficent implementation of the method proposed in "The Era of 1-bit LLMs"β154Updated 10 months ago
- The evaluation framework for training-free sparse attention in LLMsβ90Updated 2 months ago
- Google TPU optimizations for transformers modelsβ118Updated 7 months ago
- PTX-Tutorial Written Purely By AIs (Deep Research of Openai and Claude 3.7)β66Updated 5 months ago
- Work in progress.β72Updated last month
- Memory optimized Mixture of Expertsβ54Updated 3 weeks ago
- β51Updated 9 months ago
- Docker image NVIDIA GH200 machines - optimized for vllm serving and hf trainer finetuningβ47Updated 6 months ago
- NanoGPT-speedrunning for the poor T4 enjoyersβ69Updated 4 months ago
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"β244Updated 6 months ago
- CUDA and Triton implementations of Flash Attention with SoftmaxN.β73Updated last year
- β12Updated 6 months ago
- Simple and efficient DeepSeek V3 SFT using pipeline parallel and expert parallel, with both FP8 and BF16 trainingsβ76Updated 3 weeks ago
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.β19Updated last month
- Code for the examples presented in the talk "Training a Llama in your backyard: fine-tuning very large models on consumer hardware" givenβ¦β14Updated last year
- β61Updated 5 months ago
- RWKV-7: Surpassing GPTβ94Updated 9 months ago
- Simple & Scalable Pretraining for Neural Architecture Researchβ287Updated 2 weeks ago
- A repository to unravel the language of GPUs, making their kernel conversations easy to understandβ190Updated 2 months ago
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top ofβ¦β141Updated last year