efeslab / NanoflowLinks
A throughput-oriented high-performance serving framework for LLMs
☆904Updated last month
Alternatives and similar repositories for Nanoflow
Users that are interested in Nanoflow 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.☆916Updated last year
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆766Updated 7 months ago
- Materials for learning SGLang☆615Updated 3 weeks ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆428Updated last week
- Disaggregated serving system for Large Language Models (LLMs).☆706Updated 6 months ago
- Perplexity GPU Kernels☆497Updated last month
- Efficient and easy multi-instance LLM serving☆497Updated last month
- LLM KV cache compression made easy☆660Updated this week
- Distributed Compiler based on Triton for Parallel Systems☆1,173Updated 3 weeks ago
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,141Updated 3 weeks ago
- A low-latency & high-throughput serving engine for LLMs☆431Updated last week
- A PyTorch Native LLM Training Framework☆875Updated last month
- Zero Bubble Pipeline Parallelism☆432Updated 5 months ago
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆567Updated last year
- Latency and Memory Analysis of Transformer Models for Training and Inference☆459Updated 6 months ago
- Ring attention implementation with flash attention☆901Updated last month
- Serverless LLM Serving for Everyone.☆561Updated this week
- ☆205Updated 5 months ago
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆698Updated 2 months ago
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,145Updated last month
- A large-scale simulation framework for LLM inference☆459Updated 2 months ago
- Microsoft Automatic Mixed Precision Library☆626Updated last year
- kernels, of the mega variety☆586Updated 3 weeks ago
- NVIDIA Inference Xfer Library (NIXL)☆673Updated this week
- A high-performance inference system for large language models, designed for production environments.☆479Updated 2 weeks ago
- Serving multiple LoRA finetuned LLM as one☆1,101Updated last year
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆389Updated last year
- Efficient LLM Inference over Long Sequences☆390Updated 3 months ago
- A Quirky Assortment of CuTe Kernels☆627Updated last week
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆576Updated last week