infinigence / SpecEELinks
Repo for SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting (ISCA25)
☆36Updated last month
Alternatives and similar repositories for SpecEE
Users that are interested in SpecEE are comparing it to the libraries listed below
Sorting:
- ☆73Updated 2 weeks ago
- A lightweight design for computation-communication overlap.☆132Updated 3 weeks ago
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆36Updated last month
- Examples of CUDA implementations by Cutlass CuTe☆188Updated 4 months ago
- Code Repository of Evaluating Quantized Large Language Models☆123Updated 8 months ago
- ☆146Updated 10 months ago
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆81Updated 2 weeks ago
- Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"☆133Updated 2 weeks ago
- Summary of some awesome work for optimizing LLM inference☆73Updated this week
- ☆121Updated 5 months ago
- llm theoretical performance analysis tools and support params, flops, memory and latency analysis.☆92Updated this week
- High performance Transformer implementation in C++.☆124Updated 4 months ago
- ☆62Updated 11 months ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆79Updated 3 weeks ago
- Implement Flash Attention using Cute.☆85Updated 5 months ago
- Optimize softmax in triton in many cases☆20Updated 8 months ago
- ☆148Updated 4 months ago
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆253Updated 2 months ago
- Curated collection of papers in MoE model inference☆187Updated 3 months ago
- ☆108Updated last week
- ☆142Updated 5 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆211Updated last year
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆50Updated 2 weeks ago
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆39Updated 3 weeks ago
- LLM Inference analyzer for different hardware platforms☆69Updated last week
- A Vectorized N:M Format for Unleashing the Power of Sparse Tensor Cores☆51Updated last year
- This repository is established to store personal notes and annotated papers during daily research.☆125Updated last week
- ☆142Updated 11 months ago
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆47Updated 2 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆124Updated last month