kroggen / mamba-cpuLinks
Modified Mamba code to run on CPU
☆30Updated last year
Alternatives and similar repositories for mamba-cpu
Users that are interested in mamba-cpu are comparing it to the libraries listed below
Sorting:
- Inference of Mamba models in pure C☆192Updated last year
- Implementation of mamba with rust☆88Updated last year
- RWKV-7: Surpassing GPT☆100Updated last year
- RWKV in nanoGPT style☆195Updated last year
- PyTorch implementation of models from the Zamba2 series.☆185Updated 9 months ago
- https://x.com/BlinkDL_AI/status/1884768989743882276☆28Updated 6 months ago
- An efficent implementation of the method proposed in "The Era of 1-bit LLMs"☆154Updated last year
- A single repo with all scripts and utils to train / fine-tune the Mamba model with or without FIM☆60Updated last year
- The simplest, fastest repository for training/finetuning medium-sized xLSTMs.☆41Updated last year
- PB-LLM: Partially Binarized Large Language Models☆156Updated last year
- RWKV, in easy to read code☆72Updated 7 months ago
- ☆80Updated last year
- Course Project for COMP4471 on RWKV☆17Updated last year
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"☆249Updated 9 months ago
- A large-scale RWKV v7(World, PRWKV, Hybrid-RWKV) inference. Capable of inference by combining multiple states(Pseudo MoE). Easy to deploy…☆45Updated 3 weeks ago
- QuIP quantization☆60Updated last year
- ☆62Updated 4 months ago
- Thin wrapper around GGML to make life easier☆40Updated 2 weeks ago
- ☆153Updated 4 months ago
- Implementation of MambaByte in "MambaByte: Token-free Selective State Space Model" in Pytorch and Zeta☆124Updated 3 weeks ago
- RWKV-LM-V7(https://github.com/BlinkDL/RWKV-LM) Under Lightning Framework☆46Updated 3 weeks ago
- ☆136Updated last year
- Samples of good AI generated CUDA kernels☆91Updated 5 months ago
- Work in progress.☆75Updated 4 months ago
- An open source implementation of LFMs from Liquid AI: Liquid Foundation Models☆193Updated this week
- Inference RWKV v7 in pure C.☆41Updated last month
- Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.☆202Updated last year
- The homepage of OneBit model quantization framework.☆194Updated 9 months ago
- Prepare for DeekSeek R1 inference: Benchmark CPU, DRAM, SSD, iGPU, GPU, ... with efficient code.☆73Updated 9 months ago
- Train your own small bitnet model☆74Updated last year