Alternatives and similar repositories for CPM.cu

Users that are interested in CPM.cu are comparing it to the libraries listed below

• zhaochenyang20 / ModelServer
  Efficient, Flexible, and Highly Fault-Tolerant Model Service Management Based on SGLang
  ☆53Updated 7 months ago
• JT-Ushio / MHA2MLA
  Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs
  ☆176Updated this week
• madsys-dev / deepseekv2-profile
  ☆141Updated 3 months ago
• InternLM / turbomind
  ☆86Updated 2 months ago
• HandH1998 / QQQ
  QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
  ☆128Updated 2 months ago
• IsaacRe / vllm-kvcompress
  KV cache compression for high-throughput LLM inference
  ☆130Updated 4 months ago
• Infini-AI-Lab / MagicDec
  [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
  ☆116Updated 6 months ago
• microsoft / AttentionEngine
  ☆71Updated last month
• thunlp / Ouroboros
  Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)
  ☆106Updated 3 months ago
• ByteDance-Seed / FlexPrefill
  Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
  ☆113Updated last month
• neuralmagic / AutoFP8
  ☆194Updated last month
• ByteDance-Seed / decoupleQ
  A quantization algorithm for LLM
  ☆141Updated last year
• feifeibear / LLMRoofline
  Compare different hardware platforms via the Roofline Model for LLM inference tasks.
  ☆100Updated last year
• inferflow / inferflow
  Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).
  ☆242Updated last year
• SkyworkAI / Skywork-MoE
  Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models
  ☆133Updated last year
• OpenGVLab / EfficientQAT
  [ACL 2025 Main] EfficientQAT: Efficient Quantization-Aware Training for Large Language Models
  ☆273Updated last month
• xlite-dev / ffpa-attn
  ⚡️FFPA: Extend FlashAttention-2 with Split-D, achieve ~O(1) SRAM complexity for large headdim, 1.8x~3x↑ vs SDPA.
  ☆186Updated last month
• microsoft / SeerAttention
  SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs
  ☆126Updated last week
• efeslab / Atom
  [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving
  ☆310Updated 11 months ago
• DD-DuDa / BitDistiller
  [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.
  ☆115Updated last year
• PKU-SEC-Lab / HybriMoE
  [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"
  ☆54Updated last week
• AniZpZ / AutoSmoothQuant
  An easy-to-use package for implementing SmoothQuant for LLMs
  ☆100Updated 2 months ago
• FasterDecoding / SnapKV
  ☆256Updated last year
• flashinfer-ai / cutlass-viz
  ☆60Updated last month
• feifeibear / Odysseus-Transformer
  Odysseus: Playground of LLM Sequence Parallelism
  ☆70Updated last year
• wdlctc / headinfer
  ☆49Updated last month
• sihyeong / Awesome-LLM-Inference-Engine
  ☆78Updated last week
• interestingLSY / swiftLLM
  A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …
  ☆224Updated 2 weeks ago
• ruikangliu / FlatQuant
  [ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"
  ☆137Updated last month
• NVlabs / COAT
  [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training
  ☆209Updated last week