zhihu / ZhiLightLinks
A highly optimized LLM inference acceleration engine for Llama and its variants.
☆903Updated 4 months ago
Alternatives and similar repositories for ZhiLight
Users that are interested in ZhiLight are comparing it to the libraries listed below
Sorting:
- An acceleration library that supports arbitrary bit-width combinatorial quantization operations☆237Updated last year
- TVM Documentation in Chinese Simplified / TVM 中文文档☆2,647Updated last week
- FlagPerf is an open-source software platform for benchmarking AI chips.☆352Updated this week
- Unified KV Cache Compression Methods for Auto-Regressive Models☆1,275Updated 10 months ago
- UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g…☆957Updated this week
- Higher performance OpenAI LLM service than vLLM serve: A pure C++ high-performance OpenAI LLM service implemented with GPRS+TensorRT-LLM+…☆157Updated 6 months ago
- adds Sequence Parallelism into LLaMA-Factory☆588Updated last month
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆920Updated this week
- ☆915Updated this week
- A scalable, end-to-end training pipeline for general-purpose agents☆361Updated 4 months ago
- ☆511Updated 2 months ago
- DLRover: An Automatic Distributed Deep Learning System☆1,586Updated this week
- ☆72Updated last year
- [ICLR 2025🔥] SVD-LLM & [NAACL 2025🔥] SVD-LLM V2☆261Updated 2 months ago
- MIXQ: Taming Dynamic Outliers in Mixed-Precision Quantization by Online Prediction☆94Updated last year
- Train your Agent model via our easy and efficient framework☆1,613Updated last week
- ☆730Updated 2 weeks ago
- FlagScale is a large model toolkit based on open-sourced projects.☆404Updated last week
- DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …☆267Updated 3 months ago
- GLake: optimizing GPU memory management and IO transmission.☆489Updated 7 months ago
- Deep Learning Deployment Framework: Supports tf/torch/trt/trtllm/vllm and other NN frameworks. Support dynamic batching, and streaming mo…☆167Updated 6 months ago
- xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism☆2,390Updated this week
- ☆196Updated last month
- ☆75Updated 11 months ago
- minimal-cost for training 0.5B R1-Zero☆784Updated 6 months ago
- ☆13Updated 5 months ago
- [ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference☆270Updated 6 months ago
- [EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLM, VLM, and video generation models.☆614Updated this week
- ☆322Updated 2 months ago
- Extending eBPF Programmability and Observability to GPUs (merged into https://github.com/eunomia-bpf/bpftime)☆266Updated last month