Alternatives and similar repositories for candle-flash-attn-v3

Users that are interested in candle-flash-attn-v3 are comparing it to the libraries listed below

• huggingface / kernel-builder
  👷 Build compute kernels
  ☆106Updated last week
• chenwanqq / candle-llava
  implement llava using candle
  ☆15Updated last year
• facebookresearch / fastgen
  Simple high-throughput inference library
  ☆127Updated 3 months ago
• Oxen-AI / GRPO-With-Cargo-Feedback
  This repository has code for fine-tuning LLMs with GRPO specifically for Rust Programming using cargo as feedback
  ☆101Updated 5 months ago
• kyutai-labs / kaudio
  Rust crate for some audio utilities
  ☆26Updated 5 months ago
• Dan-wanna-M / kbnf
  A high-performance constrained decoding engine based on context free grammar in Rust
  ☆55Updated 3 months ago
• kyutai-labs / moshi-webrtc
  Proof of concept for running moshi/hibiki using webrtc
  ☆20Updated 5 months ago
• fbilhaut / gline-rs
  Inference engine for GLiNER models, in Rust
  ☆64Updated last month
• eugenehp / gpu-fft
  GPU based FFT written in Rust and CubeCL
  ☆23Updated 2 months ago
• cloneofsimo / ptx-tutorial-by-aislop
  PTX-Tutorial Written Purely By AIs (Deep Research of Openai and Claude 3.7)
  ☆66Updated 5 months ago
• lianakoleva / no-libtorch-compile
  ☆21Updated 5 months ago
• opendatahub-io / vllm-tgis-adapter
  vLLM adapter for a TGIS-compatible gRPC server.
  ☆37Updated this week
• atoma-network / atoma-infer
  Fast serverless LLM inference, in Rust.
  ☆88Updated 5 months ago
• beowolx / rensa
  High-performance MinHash implementation in Rust with Python bindings for efficient similarity estimation and deduplication of large datas…
  ☆199Updated last month
• huggingface / kernels
  Load compute kernels from the Hub
  ☆244Updated this week
• leo-du / llama2.rs
  Inference Llama 2 in one file of zero-dependency, zero-unsafe Rust
  ☆38Updated 2 years ago
• argilla-io / distilabel-spin-dibt
  Repository containing the SPIN experiments on the DIBT 10k ranked prompts
  ☆24Updated last year
• Systemcluster / kitoken
  Fast and versatile tokenizer for language models, compatible with SentencePiece, Tokenizers, Tiktoken and more. Supports BPE, Unigram and…
  ☆29Updated 5 months ago
• AnswerDotAI / cold-compress
  Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…
  ☆141Updated last year
• huggingface / candle-paged-attention
  ☆12Updated last year
• bertmaher / llama2.so
  Inference Llama 2 with a model compiled to native code by TorchInductor
  ☆14Updated last year
• softmax1 / Flash-Attention-Softmax-N
  CUDA and Triton implementations of Flash Attention with SoftmaxN.
  ☆73Updated last year
• cray-lm / cray-lm
  Cray-LM unified training and inference stack.
  ☆22Updated 6 months ago
• foundation-model-stack / fastsafetensors
  High-performance safetensors model loader
  ☆53Updated last month
• Narsil / bindgen_cuda
  ☆24Updated 4 months ago
• PrimeIntellect-ai / pccl
  PCCL (Prime Collective Communications Library) implements fault tolerant collective communications over IP
  ☆106Updated this week
• IBM / text-generation-inference
  IBM development fork of https://github.com/huggingface/text-generation-inference
  ☆61Updated 3 months ago
• UmerHA / triton_util
  Make triton easier
  ☆47Updated last year
• Narsil / bloomserver
  ☆39Updated 2 years ago
• guidance-ai / llgtrt
  TensorRT-LLM server with Structured Outputs (JSON) built with Rust
  ☆58Updated 4 months ago