IST-DASLab / marlinLinks
FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
☆831Updated 8 months ago
Alternatives and similar repositories for marlin
Users that are interested in marlin 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…☆686Updated 2 months ago
- A throughput-oriented high-performance serving framework for LLMs☆814Updated 3 weeks ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆384Updated this week
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆355Updated 9 months ago
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆619Updated 3 weeks ago
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆390Updated 6 months ago
- ☆536Updated 7 months ago
- Official implementation of Half-Quadratic Quantization (HQQ)☆814Updated last week
- A low-latency & high-throughput serving engine for LLMs☆370Updated this week
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆471Updated 8 months ago
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆689Updated 9 months ago
- ☆193Updated 3 weeks ago
- Latency and Memory Analysis of Transformer Models for Training and Inference☆421Updated last month
- Materials for learning SGLang☆424Updated last week
- Microsoft Automatic Mixed Precision Library☆602Updated 8 months ago
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3.☆1,277Updated this week
- Perplexity GPU Kernels☆324Updated last week
- Fast low-bit matmul kernels in Triton☆303Updated last week
- Ring attention implementation with flash attention☆771Updated last week
- The Triton TensorRT-LLM Backend☆842Updated this week
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆305Updated 11 months ago
- ☆322Updated last year
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,249Updated 2 months ago
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,040Updated this week
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆251Updated 7 months ago
- Serving multiple LoRA finetuned LLM as one☆1,060Updated last year
- GPTQ inference Triton kernel☆300Updated 2 years ago
- Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees"☆365Updated last year
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,417Updated 10 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆506Updated last week