antgroup / glakeLinks
GLake: optimizing GPU memory management and IO transmission.
☆469Updated 3 months ago
Alternatives and similar repositories for glake
Users that are interested in glake are comparing it to the libraries listed below
Sorting:
- Efficient and easy multi-instance LLM serving☆440Updated this week
- Disaggregated serving system for Large Language Models (LLMs).☆629Updated 2 months ago
- ☆435Updated this week
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆804Updated 3 weeks ago
- FlagScale is a large model toolkit based on open-sourced projects.☆308Updated this week
- Materials for learning SGLang☆463Updated last week
- Dynamic Memory Management for Serving LLMs without PagedAttention☆398Updated last month
- A low-latency & high-throughput serving engine for LLMs☆382Updated last month
- KV cache store for distributed LLM inference☆276Updated 3 weeks ago
- AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…☆247Updated 3 weeks ago
- Easy Parallel Library (EPL) is a general and efficient deep learning framework for distributed model training.☆267Updated 2 years ago
- ☆128Updated 6 months ago
- TePDist (TEnsor Program DISTributed) is an HLO-level automatic distributed system for DL models.☆94Updated 2 years ago
- Distributed Compiler Based on Triton for Parallel Systems☆857Updated 2 weeks ago
- FlagGems is an operator library for large language models implemented in the Triton Language.☆594Updated this week
- A PyTorch Native LLM Training Framework☆824Updated 6 months ago
- optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052☆474Updated last year
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆380Updated this week
- DeepSeek-V3/R1 inference performance simulator☆151Updated 3 months ago
- NVIDIA Inference Xfer Library (NIXL)☆435Updated this week
- Zero Bubble Pipeline Parallelism☆399Updated last month
- Perplexity GPU Kernels☆380Updated 3 weeks ago
- paper and its code for AI System☆312Updated 2 months ago
- ☆148Updated 5 months ago
- ☆139Updated last year
- FlagPerf is an open-source software platform for benchmarking AI chips.☆340Updated 2 weeks ago
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆90Updated last month
- A large-scale simulation framework for LLM inference☆394Updated last week
- A model compilation solution for various hardware☆438Updated last week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆991Updated last month