High-performance safetensors model loader
☆185Nov 18, 2026Updated this 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☆95Nov 12, 2026Updated last week
- ☆412Updated 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…☆205Updated this week
- NVIDIA Inference Xfer Library (NIXL)☆1,371Updated this week
- Fast and memory-efficient exact attention☆23Updated 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.
- Module, Model, and Tensor Serialization/Deserialization☆329Updated this week
- KV cache store for distributed LLM inference☆457Sep 16, 2026Updated 2 months ago
- NVIDIA GPUDirect Storage Driver☆392Oct 20, 2026Updated last month
- Open Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, T…☆529Updated this week
- Offline optimization of your disaggregated Dynamo graph☆469Oct 29, 2026Updated 3 weeks ago
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆50May 13, 2025Updated last year
- Snapshot gets GPU pods ready in seconds instead of minutes — by restoring a fully initialized GPU worker instead of starting one from scr…☆177Updated this week
- [WIP] Better (FP8) attention for Hopper☆33Aug 21, 2026Updated 3 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆528Aug 24, 2026Updated 2 months ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆7,090Updated this week
- ☆54May 19, 2025Updated last year
- CUDA checkpoint and restore utility☆510Updated this week
- High-throughput tensor loading for PyTorch☆272Oct 9, 2026Updated last month
- ☆86Updated this week
- FlashInfer: Kernel Library for LLM Serving☆6,973Updated this week
- A tool for coordinated checkpoint/restore of distributed applications with CRIU☆36Jul 31, 2026Updated 3 months ago
- Efficient and unified implementations for TopK-based sparse attention☆42Jul 10, 2026Updated 4 months ago
- ☆15Jul 10, 2026Updated 4 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- A lightweight design for computation-communication overlap.☆253Jan 20, 2026Updated 10 months ago
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆335Oct 14, 2026Updated last month
- ☆13Mar 26, 2024Updated 2 years ago
- htop-like TUI for real-time RDMA network monitoring.☆129Nov 11, 2026Updated last week
- Kubernetes CSI Driver for serving OCI model artifacts☆30May 25, 2026Updated 5 months ago
- ☆31Apr 5, 2026Updated 7 months ago
- High performance RMSNorm Implement by using SM Core Storage(Registers and Shared Memory)☆31Jan 22, 2026Updated 9 months ago
- A Datacenter Scale Distributed Inference Serving Framework☆8,539Updated this week
- 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…☆56Aug 25, 2026Updated 2 months ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- ☆98Mar 26, 2025Updated last year
- 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 8 months ago
- Allow torch tensor memory to be released and resumed later☆285Updated this week
- (ECCV 2026): Official code for Flash-BoN: Instant Drafts for Inference-Time Scaling in Diffusion Models☆26Jul 9, 2026Updated 4 months ago
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,905Sep 24, 2026Updated last month
- Open Source AI Accelerator Research Platform Standard / 开源推理研究平台☆2,066Updated this week
- LeaderWorkerSet & DisaggregatedSet: Kubernetes APIs for Distributed and Disaggregated AI Serving☆909Updated this week
Are these results useful?