NVIDIA / kvpressLinks
LLM KV cache compression made easy
☆642Updated this week
Alternatives and similar repositories for kvpress
Users that are interested in kvpress are comparing it to the libraries listed below
Sorting:
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆760Updated 7 months ago
- Efficient LLM Inference over Long Sequences☆390Updated 3 months ago
- Perplexity GPU Kernels☆482Updated 2 weeks ago
- KernelBench: Can LLMs Write GPU Kernels? - Benchmark with Torch -> CUDA problems☆592Updated this week
- Fast low-bit matmul kernels in Triton☆376Updated last week
- A throughput-oriented high-performance serving framework for LLMs☆894Updated 3 weeks ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆385Updated last year
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆493Updated 7 months ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆326Updated last week
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆269Updated 2 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆412Updated last week
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆552Updated last week
- Applied AI experiments and examples for PyTorch☆296Updated last month
- kernels, of the mega variety☆563Updated last week
- Cataloging released Triton kernels.☆261Updated 3 weeks ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆424Updated 4 months ago
- A Quirky Assortment of CuTe Kernels☆603Updated last week
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆338Updated 2 months ago
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆430Updated 10 months ago
- ArcticInference: vLLM plugin for high-throughput, low-latency inference☆270Updated this week
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆320Updated last year
- Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024☆338Updated 5 months ago
- ☆811Updated this week
- A low-latency & high-throughput serving engine for LLMs☆424Updated 4 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆905Updated last year
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆140Updated 7 months ago
- ☆242Updated this week
- Ring attention implementation with flash attention☆885Updated 3 weeks ago
- Collection of kernels written in Triton language☆157Updated 6 months ago
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆213Updated last week