hyhuang00 / moe_inference
Code Repository for the NeurIPS 2024 Paper "Toward Efficient Inference for Mixture of Experts".
☆16Updated 5 months ago
Alternatives and similar repositories for moe_inference:
Users that are interested in moe_inference are comparing it to the libraries listed below
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆36Updated 3 weeks ago
- SQUEEZED ATTENTION: Accelerating Long Prompt LLM Inference☆46Updated 5 months ago
- Implement some method of LLM KV Cache Sparsity☆32Updated 10 months ago
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆49Updated last year
- ☆68Updated 3 months ago
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆72Updated 3 months ago
- Code Repository of Evaluating Quantized Large Language Models☆121Updated 7 months ago
- Implement Flash Attention using Cute.☆76Updated 4 months ago
- AFPQ code implementation☆20Updated last year
- [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.☆109Updated 11 months ago
- ☆53Updated last year
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆33Updated last month
- GPU operators for sparse tensor operations☆32Updated last year
- Official Repo for SparseLLM: Global Pruning of LLMs (NeurIPS 2024)☆56Updated last month
- Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"☆123Updated last month
- 16-fold memory access reduction with nearly no loss☆91Updated last month
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆94Updated last week
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆42Updated last month
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆35Updated last week
- Summary of system papers/frameworks/codes/tools on training or serving large model☆56Updated last year
- Quantized Attention on GPU☆45Updated 5 months ago
- LLM Inference with Microscaling Format☆21Updated 5 months ago
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆37Updated 10 months ago
- ☆67Updated this week
- Official PyTorch implementation of "Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models"☆28Updated this week
- ☆63Updated 5 months ago
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆129Updated 2 months ago
- ☆55Updated 2 weeks ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆116Updated 2 weeks ago
- ☆40Updated 9 months ago