foundation-model-stack / fastsafetensorsLinks
High-performance safetensors model loader
☆52Updated 2 weeks ago
Alternatives and similar repositories for fastsafetensors
Users that are interested in fastsafetensors are comparing it to the libraries listed below
Sorting:
- ☆30Updated 3 months ago
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆176Updated last week
- CUDA checkpoint and restore utility☆353Updated 6 months ago
- The driver for LMCache core to run in vLLM☆45Updated 5 months ago
- A safetensors extension to efficiently store sparse quantized tensors on disk☆141Updated this week
- Module, Model, and Tensor Serialization/Deserialization☆250Updated this week
- DeeperGEMM: crazy optimized version☆70Updated 2 months ago
- A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.☆200Updated this week
- extensible collectives library in triton☆88Updated 4 months ago
- NVIDIA Inference Xfer Library (NIXL)☆491Updated this week
- ☆231Updated this week
- ☆47Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆123Updated 7 months ago
- Fast and memory-efficient exact attention☆82Updated this week
- Boosting 4-bit inference kernels with 2:4 Sparsity☆80Updated 10 months ago
- 🏙 Interactive performance profiling and debugging tool for PyTorch neural networks.☆64Updated 6 months ago
- ☆195Updated 2 months ago
- ☆92Updated 4 months ago
- NVIDIA Resiliency Extension is a python package for framework developers and users to implement fault-tolerant features. It improves the …☆194Updated last week
- Fast low-bit matmul kernels in Triton☆338Updated this week
- kernels, of the mega variety☆461Updated last month
- ☆120Updated last year
- KV cache store for distributed LLM inference☆303Updated last month
- KV cache compression for high-throughput LLM inference☆134Updated 5 months ago
- Aims to implement dual-port and multi-qp solutions in deepEP ibrc transport☆57Updated 2 months ago
- Perplexity GPU Kernels☆413Updated 2 weeks ago
- A Python library transfers PyTorch tensors between CPU and NVMe☆117Updated 8 months ago
- ☆52Updated 4 months ago
- ☆85Updated 8 months ago
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆193Updated this week