andrewkchan / yalmLinks
Yet Another Language Model: LLM inference in C++/CUDA, no libraries except for I/O
☆497Updated last week
Alternatives and similar repositories for yalm
Users that are interested in yalm are comparing it to the libraries listed below
Sorting:
- Perplexity GPU Kernels☆461Updated last month
- Materials for learning SGLang☆579Updated 3 weeks ago
- kernels, of the mega variety☆496Updated 3 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆756Updated 6 months ago
- A curated collection of resources, tutorials, and best practices for learning and mastering NVIDIA CUTLASS☆221Updated 4 months ago
- A throughput-oriented high-performance serving framework for LLMs☆891Updated this week
- CUDA/Metal accelerated language model inference☆613Updated 3 months ago
- Flash Attention in ~100 lines of CUDA (forward pass only)☆931Updated 8 months ago
- Fast low-bit matmul kernels in Triton☆371Updated last week
- a minimal cache manager for PagedAttention, on top of llama3.☆120Updated last year
- Dynamic Memory Management for Serving LLMs without PagedAttention☆416Updated 3 months ago
- ☆237Updated this week
- Fastest kernels written from scratch☆346Updated this week
- Cataloging released Triton kernels.☆257Updated last week
- ArcticInference: vLLM plugin for high-throughput, low-latency inference☆239Updated this week
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆673Updated last month
- Efficient LLM Inference over Long Sequences☆391Updated 2 months ago
- ☆118Updated 6 months ago
- Puzzles for learning Triton, play it with minimal environment configuration!☆508Updated 9 months ago
- A low-latency & high-throughput serving engine for LLMs☆416Updated 3 months ago
- A Quirky Assortment of CuTe Kernels☆557Updated this week
- flash attention tutorial written in python, triton, cuda, cutlass☆420Updated 4 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆898Updated last year
- CPU inference for the DeepSeek family of large language models in C++☆313Updated 3 months ago
- LLM KV cache compression made easy☆609Updated this week
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆400Updated this week
- Applied AI experiments and examples for PyTorch☆294Updated 3 weeks ago
- A curated list of resources for learning and exploring Triton, OpenAI's programming language for writing efficient GPU code.☆408Updated 6 months ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆1,632Updated this week
- 🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.☆217Updated last month