foundation-model-stack / fastsafetensorsLinks
High-performance safetensors model loader
☆92Updated 3 weeks ago
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☆401Updated 3 months ago
- Module, Model, and Tensor Serialization/Deserialization☆283Updated 4 months ago
- A safetensors extension to efficiently store sparse quantized tensors on disk☆233Updated this week
- ☆275Updated last week
- Fast and memory-efficient exact attention☆108Updated 3 weeks ago
- ☆31Updated 8 months ago
- The driver for LMCache core to run in vLLM☆58Updated 11 months ago
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆251Updated this week
- ☆206Updated 8 months ago
- ☆48Updated last year
- torchcomms: a modern PyTorch communications API☆319Updated this week
- DeeperGEMM: crazy optimized version☆74Updated 8 months ago
- Offline optimization of your disaggregated Dynamo graph☆146Updated this week
- NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process com…☆443Updated last week
- KV cache store for distributed LLM inference☆384Updated 2 months ago
- NVIDIA Inference Xfer Library (NIXL)☆801Updated this week
- extensible collectives library in triton☆91Updated 9 months ago
- ☆123Updated last year
- ☆73Updated last year
- Tilus is a tile-level kernel programming language with explicit control over shared memory and registers.☆439Updated 3 weeks ago
- Aims to implement dual-port and multi-qp solutions in deepEP ibrc transport☆73Updated 8 months ago
- LoRAFusion: Efficient LoRA Fine-Tuning for LLMs☆21Updated 3 months ago
- DeepXTrace is a lightweight tool for precisely diagnosing slow ranks in DeepEP-based environments.☆85Updated 3 weeks ago
- ☆71Updated 9 months ago
- ☆47Updated last year
- A Python library transfers PyTorch tensors between CPU and NVMe☆123Updated last year
- NVIDIA Resiliency Extension is a python package for framework developers and users to implement fault-tolerant features. It improves the …☆247Updated this week
- A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM☆190Updated this week
- Perplexity GPU Kernels☆552Updated 2 months ago
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆123Updated 2 weeks ago