andrewkchan / yalmLinks
Yet Another Language Model: LLM inference in C++/CUDA, no libraries except for I/O
☆472Updated 2 months ago
Alternatives and similar repositories for yalm
Users that are interested in yalm are comparing it to the libraries listed below
Sorting:
- kernels, of the mega variety☆481Updated 2 months ago
- Perplexity GPU Kernels☆449Updated 3 weeks ago
- Materials for learning SGLang☆549Updated last week
- A curated collection of resources, tutorials, and best practices for learning and mastering NVIDIA CUTLASS☆214Updated 3 months ago
- A throughput-oriented high-performance serving framework for LLMs☆876Updated 2 weeks ago
- Flash Attention in ~100 lines of CUDA (forward pass only)☆915Updated 8 months ago
- Fast low-bit matmul kernels in Triton☆353Updated 2 weeks ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆735Updated 5 months ago
- ☆232Updated last week
- Cataloging released Triton kernels.☆252Updated 7 months ago
- Fastest kernels written from scratch☆318Updated 4 months ago
- A Quirky Assortment of CuTe Kernels☆435Updated this week
- CUDA/Metal accelerated language model inference☆610Updated 3 months ago
- Efficient LLM Inference over Long Sequences☆390Updated 2 months ago
- ☆115Updated 5 months ago
- a minimal cache manager for PagedAttention, on top of llama3.☆119Updated last year
- flash attention tutorial written in python, triton, cuda, cutlass☆408Updated 3 months ago
- LLM KV cache compression made easy☆596Updated this week
- Dynamic Memory Management for Serving LLMs without PagedAttention☆407Updated 3 months ago
- Puzzles for learning Triton, play it with minimal environment configuration!☆497Updated 8 months ago
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆663Updated 3 weeks ago
- Applied AI experiments and examples for PyTorch☆292Updated last week
- 🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.☆211Updated 3 weeks ago
- A low-latency & high-throughput serving engine for LLMs☆408Updated 3 months ago
- ☆192Updated 7 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆344Updated this week
- Distributed Compiler based on Triton for Parallel Systems☆1,074Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆1,552Updated this week
- CUDA Matrix Multiplication Optimization☆218Updated last year
- ☆92Updated 5 months ago