Alternatives and similar repositories for tokenizers-cpp:

Users that are interested in tokenizers-cpp are comparing it to the libraries listed below

• IST-DASLab / marlin
  FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
  ☆786Updated 7 months ago
• bytedance / ByteTransformer
  optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052
  ☆471Updated last year
• neuralmagic / AutoFP8
  ☆185Updated 6 months ago
• triton-inference-server / fastertransformer_backend
  ☆411Updated last year
• wangkuiyi / huggingface-tokenizer-in-cxx
  ☆62Updated 2 years ago
• fpgaminer / GPTQ-triton
  GPTQ inference Triton kernel
  ☆300Updated last year
• NetEase-FuXi / EETQ
  Easy and Efficient Quantization for Transformers
  ☆195Updated 2 months ago
• tpoisonooo / llama.onnx
  LLaMa/RWKV onnx models, quantization and testcase
  ☆359Updated last year
• void-main / FasterTransformer
  Transformer related optimization, including BERT, GPT
  ☆59Updated last year
• OpenPPL / ppl.llm.serving
  ☆127Updated 3 months ago
• usyd-fsalab / fp6_llm
  An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).
  ☆245Updated 5 months ago
• OpenPPL / ppl.nn.llm
  ☆139Updated 11 months ago
• triton-inference-server / backend
  Common source, scripts and utilities for creating Triton backends.
  ☆312Updated 2 weeks ago
• wejoncy / QLLM
  A general 2-8 bits quantization toolbox with GPTQ/AWQ/HQQ/VPTQ, and export to onnx/onnx-runtime easily.
  ☆165Updated last week
• efeslab / Nanoflow
  A throughput-oriented high-performance serving framework for LLMs
  ☆788Updated 6 months ago
• microsoft / BitBLAS
  BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.
  ☆574Updated last month
• bytedance / effective_transformer
  Running BERT without Padding
  ☆471Updated 3 years ago
• bytedance / decoupleQ
  A quantization algorithm for LLM
  ☆138Updated 9 months ago
• microsoft / onnxconverter-common
  Common utilities for ONNX converters
  ☆265Updated 4 months ago
• triton-inference-server / vllm_backend
  ☆238Updated last week
• triton-inference-server / tensorrtllm_backend
  The Triton TensorRT-LLM Backend
  ☆817Updated last week
• HandH1998 / QQQ
  QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
  ☆110Updated this week
• jundaf2 / INT8-Flash-Attention-FMHA-Quantization
  ☆157Updated last year
• anyscale / llm-continuous-batching-benchmarks
  ☆117Updated last year
• microsoft / vattention
  Dynamic Memory Management for Serving LLMs without PagedAttention
  ☆338Updated 2 weeks ago
• intel / auto-round
  Advanced Quantization Algorithm for LLMs/VLMs.
  ☆417Updated this week
• Bruce-Lee-LY / flash_attention_inference
  Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.
  ☆35Updated last month
• triton-inference-server / onnxruntime_backend
  The Triton backend for the ONNX Runtime.
  ☆140Updated last week
• FlagOpen / FlagAttention
  A collection of memory efficient attention operators implemented in the Triton language.
  ☆259Updated 10 months ago
• mit-han-lab / omniserve
  [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…
  ☆628Updated last month