mit-han-lab / omniserveLinks
[MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention
☆760Updated 7 months ago
Alternatives and similar repositories for omniserve
Users that are interested in omniserve are comparing it to the libraries listed below
Sorting:
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆902Updated last year
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆685Updated last month
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆429Updated 10 months ago
- A throughput-oriented high-performance serving framework for LLMs☆894Updated 2 weeks ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆421Updated 4 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆383Updated last year
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆320Updated last year
- ☆338Updated last year
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆559Updated last year
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆412Updated this week
- LLM KV cache compression made easy☆623Updated this week
- Code repo for the paper "SpinQuant LLM quantization with learned rotations"☆333Updated 7 months ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆326Updated last week
- A low-latency & high-throughput serving engine for LLMs☆422Updated 4 months ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆265Updated 2 months ago
- Perplexity GPU Kernels☆476Updated 2 weeks ago
- Fast low-bit matmul kernels in Triton☆376Updated last week
- A powerful toolkit for compressing large models including LLM, VLM, and video generation models.☆576Updated last month
- Latency and Memory Analysis of Transformer Models for Training and Inference☆458Updated 5 months ago
- Materials for learning SGLang☆594Updated this week
- Microsoft Automatic Mixed Precision Library☆622Updated last year
- Distributed Compiler based on Triton for Parallel Systems☆1,148Updated last week
- Applied AI experiments and examples for PyTorch☆296Updated last month
- [ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"☆170Updated this week
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆140Updated last month
- Zero Bubble Pipeline Parallelism☆428Updated 4 months ago
- kernels, of the mega variety☆563Updated last week
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆339Updated 2 months ago
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆476Updated last year
- Disaggregated serving system for Large Language Models (LLMs).☆697Updated 5 months ago