Alternatives and similar repositories for fastertransformer_backend:

Users that are interested in fastertransformer_backend are comparing it to the libraries listed below

• void-main / FasterTransformer
  Transformer related optimization, including BERT, GPT
  ☆59Updated last year
• OpenPPL / ppl.llm.serving
  ☆127Updated 4 months ago
• OpenPPL / ppl.nn.llm
  ☆139Updated last year
• THUDM / FasterTransformer
  Transformer related optimization, including BERT, GPT
  ☆39Updated 2 years ago
• ProjectD-AI / LLaMA-Megatron-DeepSpeed
  Ongoing research training transformer language models at scale, including: BERT & GPT-2
  ☆69Updated last year
• feifeibear / LLMRoofline
  Compare different hardware platforms via the Roofline Model for LLM inference tasks.
  ☆97Updated last year
• anyscale / llm-continuous-batching-benchmarks
  ☆117Updated last year
• AniZpZ / AutoSmoothQuant
  An easy-to-use package for implementing SmoothQuant for LLMs
  ☆96Updated 2 weeks ago
• kwai / Megatron-Kwai
  [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…
  ☆52Updated 8 months ago
• madsys-dev / deepseekv2-profile
  ☆131Updated last month
• neuralmagic / AutoFP8
  ☆186Updated 6 months ago
• Rayrtfr / FasterTransformer
  Transformer related optimization, including BERT, GPT
  ☆17Updated last year
• HandH1998 / QQQ
  QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
  ☆116Updated 2 weeks ago
• Ascend / AscendSpeed
  ☆78Updated last year
• modelscope / dash-infer
  DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …
  ☆243Updated last week
• MoFHeka / LLaMA-Megatron
  A LLaMA1/LLaMA12 Megatron implement.
  ☆28Updated last year
• 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
• OpenPPL / ppl.llm.kernel.cuda
  ☆148Updated 3 months ago
• CoinCheung / gdGPT
  Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.
  ☆95Updated last year
• fanshiqing / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆120Updated 3 months ago
• cli99 / llm-analysis
  Latency and Memory Analysis of Transformer Models for Training and Inference
  ☆403Updated this week
• genggui001 / Megatron-DeepSpeed-Llama
  ☆84Updated last year
• fpgaminer / GPTQ-triton
  GPTQ inference Triton kernel
  ☆300Updated last year
• luchangli03 / export_llama_to_onnx
  export llama to onnx
  ☆121Updated 3 months ago
• triton-inference-server / fastertransformer_backend
  ☆411Updated last year
• Tlntin / ChatGLM2-6B-TensorRT
  ☆90Updated last year
• triton-inference-server / vllm_backend
  ☆246Updated last week
• inferflow / inferflow
  Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).
  ☆242Updated last year
• DeepLink-org / dlinfer
  ☆48Updated this week
• cauyxy / bilivideos
  ☆52Updated last year