Alternatives and similar repositories for KV-picoGPT:

Users that are interested in KV-picoGPT are comparing it to the libraries listed below

• jaymody / speculative-sampling
  Simple implementation of Speculative Sampling in NumPy for GPT-2.
  ☆91Updated last year
• BlinkDL / modded-nanogpt-rwkv
  RWKV-7: Surpassing GPT
  ☆79Updated 3 months ago
• IST-DASLab / SparseFinetuning
  Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry
  ☆40Updated last year
• IST-DASLab / QIGen
  Repository for CPU Kernel Generation for LLM Inference
  ☆25Updated last year
• UmerHA / triton_util
  Make triton easier
  ☆44Updated 8 months ago
• HanGuo97 / lq-lora
  ☆125Updated last year
• feifeibear / Odysseus-Transformer
  Odysseus: Playground of LLM Sequence Parallelism
  ☆64Updated 8 months ago
• IST-DASLab / Sparse-Marlin
  Boosting 4-bit inference kernels with 2:4 Sparsity
  ☆64Updated 5 months ago
• softmax1 / Flash-Attention-Softmax-N
  CUDA and Triton implementations of Flash Attention with SoftmaxN.
  ☆67Updated 8 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
• triton-lang / kernels
  ☆67Updated 3 months ago
• lessw2020 / triton_kernels_for_fun_and_profit
  Custom kernels in Triton language for accelerating LLMs
  ☆17Updated 10 months ago
• Infini-AI-Lab / MagicDec
  [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
  ☆107Updated 2 months ago
• TiledTensor / TiledBench
  Benchmark tests supporting the TiledCUDA library.
  ☆15Updated 3 months ago
• whyNLP / LCKV
  Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…
  ☆148Updated 3 weeks ago
• skypilot-org / sky-llama
  ☆25Updated last year
• pytorch-labs / tritonbench
  Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.
  ☆89Updated this week
• wangsiping97 / FastGEMV
  High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.
  ☆97Updated 7 months ago
• SJTU-IPADS / Bamboo
  Bamboo-7B Large Language Model
  ☆90Updated 10 months ago
• cchan / tccl
  extensible collectives library in triton
  ☆83Updated 4 months ago
• tanyuqian / redco
  NAACL '24 (Best Demo Paper RunnerUp) / MlSys @ NeurIPS '23 - RedCoast: A Lightweight Tool to Automate Distributed Training and Inference
  ☆64Updated 2 months ago
• mlc-ai / mlc-python
  ☆21Updated last week
• tspeterkim / paged-attention-minimal
  a minimal cache manager for PagedAttention, on top of llama3.
  ☆68Updated 5 months ago
• GindaChen / FlexFlashAttention3
  FlexAttention w/ FlashAttention3 Support
  ☆26Updated 4 months ago
• Jellyfish042 / uncheatable_eval
  Evaluating LLMs with Dynamic Data
  ☆75Updated last week
• salykova / sgemm.cu
  High-Performance SGEMM on CUDA devices
  ☆76Updated last month
• GATECH-EIC / ShiftAddLLM
  ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization
  ☆102Updated 4 months ago