Alternatives and similar repositories for AscendSpeed

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

• OpenPPL / ppl.llm.serving
  ☆127Updated 5 months ago
• void-main / FasterTransformer
  Transformer related optimization, including BERT, GPT
  ☆59Updated last year
• feifeibear / LLMRoofline
  Compare different hardware platforms via the Roofline Model for LLM inference tasks.
  ☆100Updated last year
• OpenPPL / ppl.nn.llm
  ☆138Updated last year
• InternLM / turbomind
  ☆85Updated 2 months ago
• zms1999 / SmartMoE
  A MoE impl for PyTorch, [ATC'23] SmartMoE
  ☆62Updated last year
• Rayrtfr / FasterTransformer
  Transformer related optimization, including BERT, GPT
  ☆17Updated last year
• DeepLink-org / dlinfer
  ☆49Updated this week
• THUDM / FasterTransformer
  Transformer related optimization, including BERT, GPT
  ☆39Updated 2 years ago
• fanshiqing / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆122Updated 5 months ago
• modelscope / dash-infer
  DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …
  ☆253Updated this week
• madsys-dev / deepseekv2-profile
  ☆137Updated 2 months ago
• FlagOpen / FlagScale
  FlagScale is a large model toolkit based on open-sourced projects.
  ☆280Updated this week
• Oneflow-Inc / models
  Models and examples built with OneFlow
  ☆97Updated 7 months ago
• CoinCheung / gdGPT
  Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.
  ☆95Updated last year
• volcengine / veGiantModel
  ☆217Updated last year
• zhaochenyang20 / ModelServer
  Efficient, Flexible, and Highly Fault-Tolerant Model Service Management Based on SGLang
  ☆53Updated 6 months ago
• AniZpZ / AutoSmoothQuant
  An easy-to-use package for implementing SmoothQuant for LLMs
  ☆99Updated last month
• BBuf / megatron-lm-parallel-group-playground
  ☆16Updated last year
• FlagOpen / FlagAttention
  A collection of memory efficient attention operators implemented in the Triton language.
  ☆270Updated 11 months ago
• bytedance / ByteTransformer
  optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052
  ☆473Updated last year
• kwai / Megatron-Kwai
  [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…
  ☆54Updated 10 months ago
• SkyworkAI / Skywork-MoE
  Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models
  ☆132Updated 11 months ago
• genggui001 / Megatron-DeepSpeed-Llama
  ☆84Updated last year
• HandH1998 / QQQ
  QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
  ☆124Updated last month
• 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.
  ☆37Updated 3 months ago
• feifeibear / Odysseus-Transformer
  Odysseus: Playground of LLM Sequence Parallelism
  ☆69Updated 11 months ago
• anyscale / llm-continuous-batching-benchmarks
  ☆118Updated last year
• ByteDance-Seed / decoupleQ
  A quantization algorithm for LLM
  ☆141Updated 11 months ago
• thu-pacman / SmartMoE-AE
  ATC23 AE
  ☆45Updated 2 years ago