foundation-model-stack / fastsafetensorsLinks
High-performance safetensors model loader
☆67Updated this week
Alternatives and similar repositories for fastsafetensors
Users that are interested in fastsafetensors are comparing it to the libraries listed below
Sorting:
- CUDA checkpoint and restore utility☆377Updated last month
- A safetensors extension to efficiently store sparse quantized tensors on disk☆180Updated this week
- ☆47Updated last year
- torchcomms: a modern PyTorch communications API☆103Updated this week
- ☆258Updated this week
- ☆31Updated 6 months ago
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆220Updated last week
- Fast and memory-efficient exact attention☆96Updated this week
- Offline optimization of your disaggregated Dynamo graph☆79Updated this week
- Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond☆104Updated this week
- LLM Serving Performance Evaluation Harness☆79Updated 8 months ago
- extensible collectives library in triton☆89Updated 6 months ago
- Efficient Compute-Communication Overlap for Distributed LLM Inference☆59Updated 3 weeks ago
- Module, Model, and Tensor Serialization/Deserialization☆270Updated 2 months ago
- The driver for LMCache core to run in vLLM☆54Updated 8 months ago
- ☆205Updated 5 months ago
- DeeperGEMM: crazy optimized version☆72Updated 5 months ago
- KV cache store for distributed LLM inference☆345Updated last month
- ☆60Updated 9 months ago
- NVIDIA Inference Xfer Library (NIXL)☆673Updated this week
- Make SGLang go brrr☆36Updated 3 weeks ago
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆238Updated 11 months ago
- NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process com…☆351Updated last week
- A Python library transfers PyTorch tensors between CPU and NVMe☆120Updated 10 months ago
- KV cache compression for high-throughput LLM inference☆142Updated 8 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆130Updated 10 months ago
- How to ensure correctness and ship LLM generated kernels in PyTorch☆66Updated last week
- ☆72Updated 6 months ago
- ☆121Updated last year
- Fast OS-level support for GPU checkpoint and restore☆245Updated 3 weeks ago