bytedance / ShadowKV
ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference
☆117Updated 2 weeks ago
Related projects ⓘ
Alternatives and complementary repositories for ShadowKV
- [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding☆228Updated 2 months ago
- Official Code for "SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression"☆94Updated last month
- MIXQ: Taming Dynamic Outliers in Mixed-Precision Quantization by Online Prediction☆76Updated 2 weeks ago
- An acceleration library that supports arbitrary bit-width combinatorial quantization operations☆225Updated last month
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆35Updated this week
- 16-fold memory access reduction with nearly no loss☆57Updated this week
- Awesome-LLM-KV-Cache: A curated list of 📙Awesome LLM KV Cache Papers with Codes.☆96Updated this week
- ☆42Updated 7 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆196Updated last week
- Code for Palu: Compressing KV-Cache with Low-Rank Projection☆56Updated this week
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆25Updated 4 months ago
- Quantized Attention on GPU☆29Updated last week
- A sparse attention kernel supporting mix sparse patterns☆53Updated 3 weeks ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆146Updated 4 months ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆32Updated 2 months ago
- ☆63Updated 3 months ago
- Official implementation of ICML 2024 paper "ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking".☆41Updated 4 months ago
- Materials for learning SGLang☆86Updated this week
- MagicPIG: LSH Sampling for Efficient LLM Generation☆45Updated 2 weeks ago
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆123Updated this week
- The Official Implementation of PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling☆553Updated last week
- ☆36Updated last month
- Official Repo for SparseLLM: Global Pruning of LLMs (NeurIPS 2024)☆36Updated 3 weeks ago
- Official PyTorch implementation of FlatQuant: Flatness Matters for LLM Quantization☆59Updated this week
- This is the official code repository of MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tas…☆62Updated 2 months ago
- LLM Serving Performance Evaluation Harness☆55Updated 2 months ago
- Support mixed-precsion inference with vllm☆95Updated this week
- ☆183Updated 6 months ago
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆98Updated 4 months ago
- Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆70Updated last week