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
• feifeibear / LLMRoofline
  Compare different hardware platforms via the Roofline Model for LLM inference tasks.
  ☆100Updated last year
• void-main / FasterTransformer
  Transformer related optimization, including BERT, GPT
  ☆59Updated last year
• THUDM / FasterTransformer
  Transformer related optimization, including BERT, GPT
  ☆39Updated 2 years ago
• Oneflow-Inc / models
  Models and examples built with OneFlow
  ☆97Updated 8 months ago
• CoinCheung / gdGPT
  Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.
  ☆96Updated last year
• InternLM / turbomind
  ☆86Updated 2 months ago
• BBuf / megatron-lm-parallel-group-playground
  ☆16Updated last year
• OpenPPL / ppl.nn.llm
  ☆139Updated last year
• DeepLink-org / dlinfer
  ☆51Updated last week
• zms1999 / SmartMoE
  A MoE impl for PyTorch, [ATC'23] SmartMoE
  ☆63Updated last year
• zhaochenyang20 / ModelServer
  Efficient, Flexible, and Highly Fault-Tolerant Model Service Management Based on SGLang
  ☆53Updated 7 months ago
• fanshiqing / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆127Updated 5 months ago
• madsys-dev / deepseekv2-profile
  ☆141Updated 3 months ago
• AniZpZ / AutoSmoothQuant
  An easy-to-use package for implementing SmoothQuant for LLMs
  ☆100Updated 2 months ago
• Rayrtfr / FasterTransformer
  Transformer related optimization, including BERT, GPT
  ☆17Updated last year
• kwai / Megatron-Kwai
  [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…
  ☆55Updated 10 months ago
• YellowOldOdd / SDBI
  Simple Dynamic Batching Inference
  ☆145Updated 3 years ago
• volcengine / veGiantModel
  ☆219Updated last year
• anyscale / llm-continuous-batching-benchmarks
  ☆119Updated last year
• feifeibear / Odysseus-Transformer
  Odysseus: Playground of LLM Sequence Parallelism
  ☆70Updated last year
• FlagOpen / FlagScale
  FlagScale is a large model toolkit based on open-sourced projects.
  ☆307Updated this week
• FlagOpen / FlagAttention
  A collection of memory efficient attention operators implemented in the Triton language.
  ☆272Updated last year
• genggui001 / Megatron-DeepSpeed-Llama
  ☆84Updated last year
• alibaba / ChatLearn
  A flexible and efficient training framework for large-scale alignment tasks
  ☆384Updated this week
• Ascend / torchair
  ☆14Updated 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.
  ☆38Updated 3 months ago
• OpenBMB / cpm_kernels
  ☆23Updated last year
• CalvinXKY / mfu_calculation
  A simple calculation for LLM MFU.
  ☆38Updated 3 months ago
• HandH1998 / QQQ
  QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
  ☆126Updated 2 months ago