High-performance safetensors model loader
☆181Oct 17, 2026Updated last week
Alternatives and similar repositories for fastsafetensors
Users that are interested in fastsafetensors are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- An ultra-fast, distributed Safetensors loader☆88Oct 13, 2026Updated 2 weeks ago
- ☆401Updated this week
- Model Express is a Rust-based component meant to be placed next to existing model inference systems to speed up their startup times and i…☆197Updated this week
- Module, Model, and Tensor Serialization/Deserialization☆326Jul 7, 2026Updated 3 months ago
- Fast and memory-efficient exact attention☆23Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- NVIDIA Inference Xfer Library (NIXL)☆1,344Updated this week
- KV cache store for distributed LLM inference☆449Sep 16, 2026Updated last month
- NVIDIA GPUDirect Storage Driver☆389Oct 20, 2026Updated last week
- ☆29Apr 5, 2026Updated 6 months ago
- ☆15Jul 10, 2026Updated 3 months ago
- Open Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, T…☆522Updated this week
- Phoenix is a direct hub between storage and xPU — plug in any accelerator (GPU/NPU) or AI app and stream data straight to the chip.☆30Updated this week
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆50May 13, 2025Updated last year
- A tool for coordinated checkpoint/restore of distributed applications with CRIU☆36Jul 31, 2026Updated 2 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Efficient and unified implementations for TopK-based sparse attention☆41Jul 10, 2026Updated 3 months ago
- Ulysses sequence-parallel all-to-all as a torch custom op, moved by the GPU copy engines into torch symmetric memory. Zero SM usage; 1.66…☆54Aug 25, 2026Updated 2 months ago
- ☆54May 19, 2025Updated last year
- CUDA checkpoint and restore utility☆504Jul 6, 2026Updated 3 months ago
- Offline optimization of your disaggregated Dynamo graph☆461Updated this week
- Dynamic Memory Management for Serving LLMs without PagedAttention☆526Aug 24, 2026Updated 2 months ago
- High-throughput tensor loading for PyTorch☆270Oct 9, 2026Updated 3 weeks ago
- htop-like TUI for real-time RDMA network monitoring.☆125Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,929Updated this week
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- (ECCV 2026): Official code for Flash-BoN: Instant Drafts for Inference-Time Scaling in Diffusion Models☆25Jul 9, 2026Updated 3 months ago
- A lightweight design for computation-communication overlap.☆252Jan 20, 2026Updated 9 months ago
- FlashInfer: Kernel Library for LLM Serving☆6,821Updated this week
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆332Oct 14, 2026Updated 2 weeks ago
- ☆12Mar 26, 2024Updated 2 years ago
- VUA stands for 'VAST Undivided Attention'. It's a global KVCache storage solution optimizing LLM time to first token (TTFT) and GPU utili…☆38Mar 12, 2026Updated 7 months ago
- Kubernetes CSI Driver for serving OCI model artifacts☆30May 25, 2026Updated 5 months ago
- Allow torch tensor memory to be released and resumed later☆281Sep 29, 2026Updated last month
- High performance RMSNorm Implement by using SM Core Storage(Registers and Shared Memory)☆31Jan 22, 2026Updated 9 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,878Sep 24, 2026Updated last month
- A Datacenter Scale Distributed Inference Serving Framework☆8,409Updated this week
- a size profiler for cuda binary☆74Oct 3, 2026Updated 3 weeks ago
- Modular RDMA Interface☆189Updated this week
- LeaderWorkerSet & DisaggregatedSet: Kubernetes APIs for Distributed and Disaggregated AI Serving☆897Updated this week
- A NCCL extension library, designed to efficiently offload GPU memory allocated by the NCCL communication library.☆122Dec 17, 2025Updated 10 months ago
- Open Source AI Accelerator Research Platform Standard / 开源推理研究平台☆1,946Updated this week