cornstarch-org / CornstarchLinks
☆113Updated 2 months ago
Alternatives and similar repositories for Cornstarch
Users that are interested in Cornstarch are comparing it to the libraries listed below
Sorting:
- Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024☆347Updated 6 months ago
- Simple & Scalable Pretraining for Neural Architecture Research☆302Updated last month
- Official PyTorch implementation for Hogwild! Inference: Parallel LLM Generation with a Concurrent Attention Cache☆133Updated 3 months ago
- An extension of the nanoGPT repository for training small MOE models.☆215Updated 8 months ago
- ArcticTraining is a framework designed to simplify and accelerate the post-training process for large language models (LLMs)☆254Updated this week
- ☆200Updated 11 months ago
- FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.☆305Updated 3 weeks ago
- ☆225Updated last month
- Easy, Fast, and Scalable Multimodal AI☆73Updated this week
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆358Updated 11 months ago
- Efficient LLM Inference over Long Sequences☆391Updated 5 months ago
- ArcticInference: vLLM plugin for high-throughput, low-latency inference☆321Updated this week
- Collection of scripts and notebooks for OpenAI's latest GPT OSS models☆479Updated 3 months ago
- Training-free Post-training Efficient Sub-quadratic Complexity Attention. Implemented with OpenAI Triton.☆148Updated 3 weeks ago
- Accelerating your LLM training to full speed! Made with ❤️ by ServiceNow Research☆262Updated this week
- Load compute kernels from the Hub☆335Updated this week
- Google TPU optimizations for transformers models☆122Updated 10 months ago
- Official implementation for Training LLMs with MXFP4☆109Updated 7 months ago
- ☆203Updated 11 months ago
- A compact LLM pretrained in 9 days by using high quality data☆334Updated 7 months ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆173Updated 10 months ago
- Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.☆202Updated last year
- Cray-LM unified training and inference stack.☆22Updated 9 months ago
- Reverse Engineering Gemma 3n: Google's New Edge-Optimized Language Model☆252Updated 6 months ago
- 👷 Build compute kernels☆186Updated this week
- ☆45Updated 6 months ago
- A family of compressed models obtained via pruning and knowledge distillation☆356Updated 3 weeks ago
- A repository to unravel the language of GPUs, making their kernel conversations easy to understand☆196Updated 5 months ago
- Memory optimized Mixture of Experts☆69Updated 4 months ago
- ☆182Updated 3 months ago