Alternatives and similar repositories for ModelServer

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

• OpenBMB / CPM.cu
  CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge tec…
  ☆212Updated 2 months ago
• InternLM / turbomind
  ☆97Updated 8 months ago
• madsys-dev / deepseekv2-profile
  ☆154Updated 9 months ago
• inferflow / inferflow
  Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).
  ☆250Updated last year
• microsoft / chunk-attention
  ☆83Updated 8 months ago
• gogongxt / nano-sglang
  ☆78Updated 3 weeks ago
• AniZpZ / AutoSmoothQuant
  An easy-to-use package for implementing SmoothQuant for LLMs
  ☆110Updated 8 months ago
• feifeibear / LLMRoofline
  Compare different hardware platforms via the Roofline Model for LLM inference tasks.
  ☆119Updated last year
• Bruce-Lee-LY / decoding_attention
  Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.
  ☆46Updated 6 months ago
• neuralmagic / AutoFP8
  ☆206Updated 7 months ago
• Infini-AI-Lab / MagicDec
  [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
  ☆135Updated last year
• HandH1998 / QQQ
  QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
  ☆151Updated 4 months ago
• smart-lty / ParallelSpeculativeDecoding
  [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length
  ☆137Updated last month
• rlite-project / RLite
  A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…
  ☆92Updated 3 months ago
• xlite-dev / ffpa-attn
  🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.
  ☆239Updated last month
• thunlp / Ouroboros
  Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)
  ☆112Updated 9 months ago
• casper-hansen / AutoAWQ_kernels
  ☆78Updated last year
• IsaacRe / vllm-kvcompress
  KV cache compression for high-throughput LLM inference
  ☆148Updated 10 months ago
• ModelTC / awesome-lm-system
  Summary of system papers/frameworks/codes/tools on training or serving large model
  ☆57Updated 2 years ago
• Ascend / AscendSpeed
  ☆79Updated 2 years ago
• llm-semantic-router / vllm-router
  vLLM Router
  ☆52Updated last year
• SkyworkAI / Skywork-MoE
  Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models
  ☆137Updated last year
• GeeeekExplorer / transformers-patch
  patches for huggingface transformers to save memory
  ☆32Updated 6 months ago
• CalvinXKY / mfu_calculation
  A simple calculation for LLM MFU.
  ☆50Updated 3 months ago
• vllm-project / vllm-nccl
  Manages vllm-nccl dependency
  ☆17Updated last year
• sgl-project / whl
  Kernel Library Wheel for SGLang
  ☆16Updated this week
• ByteDance-Seed / decoupleQ
  A quantization algorithm for LLM
  ☆146Updated last year
• hyperai / triton-cn
  Triton Documentation in Chinese Simplified / Triton 中文文档
  ☆95Updated this week
• mdy666 / mdy_triton
  ☆149Updated 5 months ago
• Tencent / AngelSlim
  Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.
  ☆228Updated this week