foundation-model-stack / fastsafetensorsLinks
High-performance safetensors model loader
☆76Updated 2 weeks ago
Alternatives and similar repositories for fastsafetensors
Users that are interested in fastsafetensors are comparing it to the libraries listed below
Sorting:
- ☆31Updated 7 months ago
- CUDA checkpoint and restore utility☆393Updated 2 months ago
- ☆267Updated last week
- A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM☆132Updated last week
- A safetensors extension to efficiently store sparse quantized tensors on disk☆210Updated 2 weeks ago
- torchcomms: a modern PyTorch communications API☆295Updated last week
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆234Updated this week
- KV cache store for distributed LLM inference☆368Updated 3 weeks ago
- Module, Model, and Tensor Serialization/Deserialization☆276Updated 3 months ago
- NVIDIA Inference Xfer Library (NIXL)☆740Updated this week
- Offline optimization of your disaggregated Dynamo graph☆118Updated this week
- Fast and memory-efficient exact attention☆102Updated last week
- ☆48Updated last year
- The driver for LMCache core to run in vLLM☆58Updated 10 months ago
- ☆72Updated 9 months ago
- KV cache compression for high-throughput LLM inference☆145Updated 9 months ago
- ☆72Updated 10 months ago
- ☆205Updated 6 months ago
- ☆324Updated 3 weeks ago
- Efficient and easy multi-instance LLM serving☆512Updated 3 months ago
- OME is a Kubernetes operator for enterprise-grade management and serving of Large Language Models (LLMs)☆322Updated this week
- DeeperGEMM: crazy optimized version☆73Updated 6 months ago
- LLM Serving Performance Evaluation Harness☆81Updated 9 months ago
- A high-performance RL training-inference weight synchronization framework, designed to enable second-level parameter updates from trainin…☆98Updated last week
- ArcticInference: vLLM plugin for high-throughput, low-latency inference☆327Updated this week
- ☆42Updated last week
- NVIDIA Resiliency Extension is a python package for framework developers and users to implement fault-tolerant features. It improves the …☆239Updated this week
- Perplexity GPU Kernels☆534Updated 3 weeks ago
- A Python library transfers PyTorch tensors between CPU and NVMe☆122Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆132Updated last year