IST-DASLab / qmoe
Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".
☆265Updated last year
Alternatives and similar repositories for qmoe:
Users that are interested in qmoe are comparing it to the libraries listed below
- Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees"☆361Updated 11 months ago
- Official PyTorch implementation of QA-LoRA☆126Updated 11 months ago
- An efficent implementation of the method proposed in "The Era of 1-bit LLMs"☆154Updated 4 months ago
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆229Updated this week
- Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.☆191Updated 7 months ago
- PB-LLM: Partially Binarized Large Language Models☆151Updated last year
- ☆524Updated 3 months ago
- scalable and robust tree-based speculative decoding algorithm☆332Updated 3 weeks ago
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"☆215Updated 3 weeks ago
- GPTQ inference Triton kernel☆295Updated last year
- Repository for the QUIK project, enabling the use of 4bit kernels for generative inference - EMNLP 2024☆175Updated 10 months ago
- ☆192Updated 2 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆332Updated 6 months ago
- [ICML 2024] CLLMs: Consistency Large Language Models☆372Updated 3 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆259Updated 4 months ago
- ☆181Updated this week
- ☆539Updated 2 months ago
- Multipack distributed sampler for fast padding-free training of LLMs☆184Updated 6 months ago
- EfficientQAT: Efficient Quantization-Aware Training for Large Language Models☆246Updated 4 months ago
- Experiments on speculative sampling with Llama models☆124Updated last year
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆676Updated 6 months ago
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆193Updated 3 months ago
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆342Updated 2 months ago
- Reorder-based post-training quantization for large language model☆184Updated last year
- For releasing code related to compression methods for transformers, accompanying our publications☆408Updated last month
- This repository contains the experimental PyTorch native float8 training UX☆221Updated 6 months ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆116Updated 2 months ago
- ☆217Updated 8 months ago
- ☆125Updated last year
- Fast low-bit matmul kernels in Triton☆236Updated this week