foundation-model-stack / fastsafetensorsLinks
High-performance safetensors model loader
☆62Updated 2 months ago
Alternatives and similar repositories for fastsafetensors
Users that are interested in fastsafetensors are comparing it to the libraries listed below
Sorting:
- ☆31Updated 5 months ago
- CUDA checkpoint and restore utility☆371Updated 2 weeks ago
- Module, Model, and Tensor Serialization/Deserialization☆268Updated last month
- ☆47Updated last year
- A safetensors extension to efficiently store sparse quantized tensors on disk☆164Updated this week
- Offline optimization of your disaggregated Dynamo graph☆70Updated this week
- DeeperGEMM: crazy optimized version☆71Updated 4 months ago
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆214Updated last week
- Fast and memory-efficient exact attention☆95Updated this week
- The driver for LMCache core to run in vLLM☆51Updated 7 months ago
- KV cache store for distributed LLM inference☆336Updated 3 weeks ago
- extensible collectives library in triton☆88Updated 6 months ago
- ☆74Updated 6 months ago
- ☆254Updated 2 weeks ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆128Updated 9 months ago
- KV cache compression for high-throughput LLM inference☆141Updated 7 months ago
- ☆121Updated last year
- LLM Serving Performance Evaluation Harness☆79Updated 7 months ago
- Efficient Compute-Communication Overlap for Distributed LLM Inference☆57Updated 3 weeks ago
- ☆60Updated 8 months ago
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆234Updated 10 months ago
- NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process com…☆324Updated 2 weeks ago
- [WIP] Better (FP8) attention for Hopper☆33Updated 7 months ago
- Bamboo-7B Large Language Model☆93Updated last year
- Efficient and easy multi-instance LLM serving☆491Updated last month
- kvcached: Elastic KV cache for dynamic GPU sharing and efficient multi-LLM inference.☆94Updated this week
- ☆199Updated 4 months ago
- kernels, of the mega variety☆502Updated last week
- Make SGLang go brrr☆33Updated 3 weeks ago
- ☆98Updated 4 months ago