Alternatives and similar repositories for llama-cuda-graph-example:

Users that are interested in llama-cuda-graph-example are comparing it to the libraries listed below

• IST-DASLab / Sparse-Marlin
  Boosting 4-bit inference kernels with 2:4 Sparsity
  ☆64Updated 5 months ago
• neuralmagic / compressed-tensors
  A safetensors extension to efficiently store sparse quantized tensors on disk
  ☆77Updated this week
• deepspeedai / DeepSpeed-Kernels
  ☆59Updated 2 weeks ago
• pytorch-labs / tritonbench
  Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.
  ☆89Updated this week
• stanford-futuredata / stk
  ☆100Updated 5 months ago
• Infini-AI-Lab / MagicDec
  [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
  ☆107Updated 2 months ago
• cchan / tccl
  extensible collectives library in triton
  ☆83Updated 4 months ago
• siyan-zhao / prepacking
  The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models"
  ☆59Updated 4 months ago
• abacusai / gh200-llm
  Docker image NVIDIA GH200 machines - optimized for vllm serving and hf trainer finetuning
  ☆35Updated this week
• wangsiping97 / FastGEMV
  High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.
  ☆97Updated 7 months ago
• IST-DASLab / SparseFinetuning
  Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry
  ☆40Updated last year
• gpu-mode / ring-attention
  ring-attention experiments
  ☆123Updated 4 months ago
• tgale96 / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆64Updated 3 months ago
• MDK8888 / vllmini
  A minimal implementation of vllm.
  ☆33Updated 6 months ago
• dame-cell / Triformer
  Transformers components but in Triton
  ☆31Updated 3 months ago
• IBM / triton-dejavu
  Framework to reduce autotune overhead to zero for well known deployments.
  ☆61Updated 3 weeks ago
• triton-lang / kernels
  ☆67Updated 3 months ago
• microsoft / TileFusion
  TileFusion is a highly efficient kernel template library designed to elevate the level of abstraction in CUDA C for processing tiles.
  ☆56Updated this week
• ScalingIntelligence / hydragen
  Hydragen: High-Throughput LLM Inference with Shared Prefixes
  ☆34Updated 9 months ago
• PipeFusion / PipeFusion
  A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters
  ☆39Updated 6 months ago
• feifeibear / Odysseus-Transformer
  Odysseus: Playground of LLM Sequence Parallelism
  ☆64Updated 8 months ago
• UmerHA / triton_util
  Make triton easier
  ☆44Updated 8 months ago
• tyler-griggs / melange-release
  ☆43Updated 7 months ago
• ScalingIntelligence / KernelBench
  KernelBench: Can LLMs Write GPU Kernels? - Benchmark with Torch -> CUDA problems
  ☆183Updated this week
• Bruce-Lee-LY / decoding_attention
  Decoding Attention is specially optimized for multi head attention (MHA) using CUDA core for the decoding stage of LLM inference.
  ☆29Updated 3 months ago
• FasterDecoding / TEAL
  ☆111Updated last week
• SqueezeBits / QUICK
  QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference
  ☆116Updated 11 months ago
• IST-DASLab / QIGen
  Repository for CPU Kernel Generation for LLM Inference
  ☆25Updated last year