GreenBitAI / low_bit_llamaLinks
Advanced Ultra-Low Bitrate Compression Techniques for the LLaMA Family of LLMs
☆110Updated last year
Alternatives and similar repositories for low_bit_llama
Users that are interested in low_bit_llama are comparing it to the libraries listed below
Sorting:
- PB-LLM: Partially Binarized Large Language Models☆157Updated 2 years ago
- Repository for CPU Kernel Generation for LLM Inference☆27Updated 2 years ago
- QuIP quantization☆61Updated last year
- Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".☆279Updated 2 years ago
- GPTQLoRA: Efficient Finetuning of Quantized LLMs with GPTQ☆101Updated 2 years ago
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry☆42Updated last year
- Reorder-based post-training quantization for large language model☆196Updated 2 years ago
- Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees" adapted for Llama models☆41Updated 2 years ago
- ☆113Updated last month
- ☆204Updated last year
- A general 2-8 bits quantization toolbox with GPTQ/AWQ/HQQ/VPTQ, and export to onnx/onnx-runtime easily.☆184Updated 8 months ago
- Structural Pruning for LLaMA☆54Updated 2 years ago
- ☆120Updated last year
- ☆59Updated 2 years ago
- CUDA and Triton implementations of Flash Attention with SoftmaxN.☆73Updated last year
- An efficent implementation of the method proposed in "The Era of 1-bit LLMs"☆155Updated last year
- Experiments on speculative sampling with Llama models☆127Updated 2 years ago
- SparseGPT + GPTQ Compression of LLMs like LLaMa, OPT, Pythia☆41Updated 2 years ago
- ☆128Updated last year
- Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees"☆392Updated last year
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆131Updated last year
- Official repository for the paper "SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"☆102Updated last year
- ☆159Updated 6 months ago
- Get down and dirty with FlashAttention2.0 in pytorch, plug in and play no complex CUDA kernels☆112Updated 2 years ago
- ☆157Updated 2 years ago
- ☆71Updated last year
- Official code for "SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient"☆148Updated 2 years ago
- Repo hosting codes and materials related to speeding LLMs' inference using token merging.☆37Updated 2 months ago
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated 2 years ago
- Token Omission Via Attention☆128Updated last year