Ascend / AscendSpeed

Related projects: ⓘ

• void-main / FasterTransformer
  Transformer related optimization, including BERT, GPT
  ☆58Updated 11 months ago
• FlagOpen / FlagScale
  FlagScale is a large model toolkit based on open-sourced projects.
  ☆129Updated this week
• OpenPPL / ppl.llm.serving
  ☆123Updated 3 months ago
• Oneflow-Inc / models
  Models and examples built with OneFlow
  ☆94Updated last month
• alibaba / ChatLearn
  ☆105Updated this week
• THUDM / FasterTransformer
  Transformer related optimization, including BERT, GPT
  ☆39Updated last year
• feifeibear / long-context-attention
  USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference
  ☆309Updated this week
• FlagOpen / FlagAttention
  A collection of memory efficient attention operators implemented in the Triton language.
  ☆205Updated 3 months ago
• openppl-public / ppl.nn.llm
  ☆140Updated 4 months ago
• zms1999 / SmartMoE
  A MoE impl for PyTorch, [ATC'23] SmartMoE
  ☆56Updated last year
• fanshiqing / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆57Updated 2 months ago
• feifeibear / LLMRoofline
  Compare different hardware platforms via the Roofline Model for LLM inference tasks.
  ☆71Updated 6 months ago
• Rayrtfr / FasterTransformer
  Transformer related optimization, including BERT, GPT
  ☆17Updated last year
• AniZpZ / AutoSmoothQuant
  An easy-to-use package for implementing SmoothQuant for LLMs
  ☆78Updated 4 months ago
• madsys-dev / deepseekv2-profile
  ☆60Updated last month
• kwai / Megatron-Kwai
  [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…
  ☆41Updated last month
• luchangli03 / export_llama_to_onnx
  export llama to onnx
  ☆91Updated 3 months ago
• CoinCheung / gdGPT
  Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.
  ☆90Updated 7 months ago
• 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.
  ☆20Updated last week
• ModelTC / awesome-lm-system
  Summary of system papers/frameworks/codes/tools on training or serving large model
  ☆56Updated 9 months ago
• volcengine / veGiantModel
  ☆205Updated last year
• Oneflow-Inc / one-glm
  A more efficient GLM implementation!
  ☆54Updated last year
• bytedance / decoupleQ
  A quantization algorithm for LLM
  ☆98Updated 2 months ago
• genggui001 / Megatron-DeepSpeed-Llama
  ☆82Updated last year
• YellowOldOdd / SDBI
  Simple Dynamic Batching Inference
  ☆145Updated 2 years ago
• thu-pacman / SmartMoE-AE
  ATC23 AE
  ☆42Updated last year
• Ascend / pytorch
  Ascend PyTorch adapter (torch_npu). Mirror of https://gitee.com/ascend/pytorch
  ☆226Updated this week
• anyscale / llm-continuous-batching-benchmarks
  ☆108Updated 6 months ago
• pcg-mlp / KsanaLLM
  ☆251Updated last week
• neuralmagic / AutoFP8
  ☆145Updated last month