IST-DASLab / marlin
FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
☆771Updated 6 months ago
Alternatives and similar repositories for marlin:
Users that are interested in marlin are comparing it to the libraries listed below
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆611Updated 2 weeks ago
- A throughput-oriented high-performance serving framework for LLMs☆773Updated 6 months ago
- ☆310Updated 11 months ago
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆557Updated last month
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆361Updated 3 months ago
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆415Updated 6 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆336Updated 7 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆317Updated this week
- GPTQ inference Triton kernel☆298Updated last year
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3.☆1,057Updated this week
- The Triton TensorRT-LLM Backend☆809Updated this week
- ☆528Updated 4 months ago
- Serving multiple LoRA finetuned LLM as one☆1,040Updated 10 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆298Updated 8 months ago
- Disaggregated serving system for Large Language Models (LLMs).☆507Updated 7 months ago
- Fast low-bit matmul kernels in Triton☆267Updated this week
- Microsoft Automatic Mixed Precision Library☆581Updated 5 months ago
- ☆180Updated 5 months ago
- A low-latency & high-throughput serving engine for LLMs☆325Updated last month
- Official implementation of Half-Quadratic Quantization (HQQ)☆770Updated this week
- Zero Bubble Pipeline Parallelism☆373Updated 2 weeks ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆240Updated 4 months ago
- Materials for learning SGLang☆345Updated this week
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,216Updated 2 weeks ago
- For releasing code related to compression methods for transformers, accompanying our publications☆416Updated 2 months ago
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆431Updated 7 months ago
- [NeurIPS'24 Spotlight, ICLR'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which r…☆944Updated 3 weeks ago
- Latency and Memory Analysis of Transformer Models for Training and Inference☆401Updated 2 weeks ago
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆680Updated 7 months ago
- Easy and Efficient Quantization for Transformers☆193Updated last month