andrewkchan / yalmLinks
Yet Another Language Model: LLM inference in C++/CUDA, no libraries except for I/O
☆525Updated last month
Alternatives and similar repositories for yalm
Users that are interested in yalm are comparing it to the libraries listed below
Sorting:
- Perplexity GPU Kernels☆513Updated this week
- kernels, of the mega variety☆594Updated last month
- A curated collection of resources, tutorials, and best practices for learning and mastering NVIDIA CUTLASS☆233Updated 5 months ago
- Materials for learning SGLang☆626Updated last week
- Cataloging released Triton kernels.☆263Updated last month
- Fastest kernels written from scratch☆384Updated last month
- A throughput-oriented high-performance serving framework for LLMs☆909Updated this week
- ☆246Updated this week
- Fast low-bit matmul kernels in Triton☆388Updated this week
- a minimal cache manager for PagedAttention, on top of llama3.☆125Updated last year
- CUDA/Metal accelerated language model inference☆619Updated 5 months ago
- Flash Attention in ~100 lines of CUDA (forward pass only)☆959Updated 10 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆775Updated 7 months ago
- A Quirky Assortment of CuTe Kernels☆645Updated this week
- flash attention tutorial written in python, triton, cuda, cutlass☆437Updated 5 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆432Updated 5 months ago
- ☆123Updated last week
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆703Updated 2 months ago
- Applied AI experiments and examples for PyTorch☆301Updated 2 months ago
- LLM KV cache compression made easy☆669Updated last week
- Puzzles for learning Triton, play it with minimal environment configuration!☆553Updated last month
- ArcticInference: vLLM plugin for high-throughput, low-latency inference☆288Updated this week
- Distributed Compiler based on Triton for Parallel Systems☆1,206Updated 2 weeks ago
- 🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.☆226Updated 2 months ago
- Fast CUDA matrix multiplication from scratch☆917Updated last month
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆451Updated this week
- Efficient LLM Inference over Long Sequences☆390Updated 4 months ago
- A low-latency & high-throughput serving engine for LLMs☆431Updated 2 weeks ago
- KernelBench: Can LLMs Write GPU Kernels? - Benchmark with Torch -> CUDA problems☆632Updated last week
- CUDA Matrix Multiplication Optimization☆234Updated last year