Alternatives and similar repositories for sgl-kernel-npu

Users that are interested in sgl-kernel-npu are comparing it to the libraries listed below

• sgl-project / SpecForge
  Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
  ☆683Updated this week
• madsys-dev / deepseekv2-profile
  ☆155Updated 11 months ago
• kwai / Megatron-Kwai
  LLM training technologies developed by kwai
  ☆70Updated 3 weeks ago
• feifeibear / LLMRoofline
  Compare different hardware platforms via the Roofline Model for LLM inference tasks.
  ☆120Updated last year
• infinigence / Semi-PD
  A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.
  ☆123Updated last month
• stepfun-ai / StepMesh
  ☆342Updated 2 weeks ago
• fzyzcjy / torch_memory_saver
  Allow torch tensor memory to be released and resumed later
  ☆216Updated 3 weeks ago
• AlibabaPAI / FLASHNN
  ☆105Updated last year
• sunkx109 / GPUs-Specs
  Summary of the Specs of Commonly Used GPUs for Training and Inference of LLM
  ☆75Updated 6 months ago
• LLMServe / SwiftTransformer
  High performance Transformer implementation in C++.
  ☆151Updated last year
• AlibabaPAI / torchacc
  PyTorch distributed training acceleration framework
  ☆55Updated 5 months ago
• Tencent / hpc-ops
  High Performance LLM Inference Operator Library
  ☆695Updated last week
• flagos-ai / FlagCX
  FlagCX is a scalable and adaptive cross-chip communication library.
  ☆172Updated this week
• antgroup / DeepXTrace
  DeepXTrace is a lightweight tool for precisely diagnosing slow ranks in DeepEP-based environments.
  ☆92Updated 3 weeks ago
• tile-ai / tilelang-ascend
  Ascend TileLang adapter
  ☆217Updated this week
• flagos-ai / FlagScale
  FlagScale is a large model toolkit based on open-sourced projects.
  ☆474Updated this week
• harleyszhang / llm_counts
  llm theoretical performance analysis tools and support params, flops, memory and latency analysis.
  ☆115Updated 7 months ago
• infinigence / FlashOverlap
  A lightweight design for computation-communication overlap.
  ☆219Updated 3 weeks ago
• zartbot / shallowsim
  DeepSeek-V3/R1 inference performance simulator
  ☆176Updated 10 months ago
• antgroup / sglang
  SGLang is a fast serving framework for large language models and vision language models.
  ☆28Updated this week
• Ascend / triton-ascend
  Triton adapter for Ascend. Mirror of https://gitee.com/ascend/triton-ascend
  ☆107Updated this week
• sgl-project / sgl-learning-materials
  Materials for learning SGLang
  ☆738Updated last month
• fzyzcjy / torch_utils
  Utility scripts for PyTorch (e.g. Make Perfetto show some disappearing kernels, Memory profiler that understands more low-level allocatio…
  ☆83Updated 5 months ago
• AlibabaPAI / llumnix
  Efficient and easy multi-instance LLM serving
  ☆524Updated 5 months ago
• shenh10 / DeepSeek_Simulator
  ☆95Updated 10 months ago
• LDLINGLINGLING / nano_vllm_note
  注释的nano_vllm仓库，并且完成了MiniCPM4的适配以及注册新模型的功能
  ☆158Updated 6 months ago
• Victarry / PP-Schedule-Visualization
  Pipeline Parallelism Emulation and Visualization
  ☆77Updated last month
• DeepLink-org / DLSlime
  DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit
  ☆92Updated 2 weeks ago
• InternLM / turbomind
  ☆96Updated 10 months ago
• antgroup / glake
  GLake: optimizing GPU memory management and IO transmission.
  ☆497Updated 10 months ago