andrewkchan / yalmLinks
Yet Another Language Model: LLM inference in C++/CUDA, no libraries except for I/O
☆359Updated 4 months ago
Alternatives and similar repositories for yalm
Users that are interested in yalm are comparing it to the libraries listed below
Sorting:
- Perplexity GPU Kernels☆324Updated 2 weeks ago
- A throughput-oriented high-performance serving framework for LLMs☆814Updated 3 weeks ago
- Efficient LLM Inference over Long Sequences☆376Updated this week
- Materials for learning SGLang☆424Updated last week
- kernels, of the mega variety☆329Updated this week
- A curated collection of resources, tutorials, and best practices for learning and mastering NVIDIA CUTLASS☆181Updated 3 weeks ago
- Fast low-bit matmul kernels in Triton☆303Updated last week
- CUDA/Metal accelerated language model inference☆581Updated this week
- Fastest kernels written from scratch☆269Updated 2 months ago
- Flash Attention in ~100 lines of CUDA (forward pass only)☆833Updated 5 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆686Updated 2 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆384Updated this week
- Cataloging released Triton kernels.☆226Updated 4 months ago
- Distributed Triton for Parallel Systems☆775Updated this week
- A low-latency & high-throughput serving engine for LLMs☆370Updated this week
- ☆210Updated this week
- CPU inference for the DeepSeek family of large language models in C++☆296Updated this week
- ☆105Updated 2 months ago
- An experimental CPU backend for Triton☆118Updated last month
- KV cache store for distributed LLM inference☆250Updated this week
- Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA☆850Updated this week
- KernelBench: Can LLMs Write GPU Kernels? - Benchmark with Torch -> CUDA problems☆351Updated 3 weeks ago
- a minimal cache manager for PagedAttention, on top of llama3.☆89Updated 9 months ago
- ☆210Updated 4 months ago
- flash attention tutorial written in python, triton, cuda, cutlass☆368Updated 3 weeks ago
- Applied AI experiments and examples for PyTorch☆271Updated this week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆831Updated 8 months ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆1,225Updated this week
- KV cache compression for high-throughput LLM inference☆129Updated 3 months ago
- VPTQ, A Flexible and Extreme low-bit quantization algorithm☆637Updated last month