Alternatives and similar repositories for UMbreLLa

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

• Cornell-RelaxML / qtip
  ☆163Updated 7 months ago
• eqimp / hogwild_llm
  Official PyTorch implementation for Hogwild! Inference: Parallel LLM Generation with a Concurrent Attention Cache
  ☆140Updated 5 months ago
• IsaacRe / vllm-kvcompress
  KV cache compression for high-throughput LLM inference
  ☆151Updated last year
• Cornell-RelaxML / yaqa-quantization
  ☆71Updated 7 months ago
• ScalingIntelligence / good-kernels
  Samples of good AI generated CUDA kernels
  ☆99Updated 8 months ago
• NimbleEdge / sparse_transformers
  Sparse Inferencing for transformer based LLMs
  ☆218Updated 5 months ago
• Infini-AI-Lab / Sequoia
  scalable and robust tree-based speculative decoding algorithm
  ☆366Updated last year
• arcee-ai / PruneMe
  Automated Identification of Redundant Layer Blocks for Pruning in Large Language Models
  ☆260Updated last year
• wdlctc / headinfer
  ☆64Updated 8 months ago
• z-lab / dflash
  Block Diffusion for Ultra-Fast Speculative Decoding
  ☆459Updated this week
• IST-DASLab / MoE-Quant
  Code for data-aware compression of DeepSeek models
  ☆69Updated last month
• DeepAuto-AI / hip-attention
  Training-free Post-training Efficient Sub-quadratic Complexity Attention. Implemented with OpenAI Triton.
  ☆148Updated 3 months ago
• efeslab / fiddler
  [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration
  ☆258Updated last year
• snu-mllab / KVzip
  [NeurIPS'25 Oral] Query-agnostic KV cache eviction: 3–4× reduction in memory and 2× decrease in latency (Qwen3/2.5, Gemma3, LLaMA3)
  ☆196Updated 2 weeks ago
• CerebrasResearch / reap
  REAP: Router-weighted Expert Activation Pruning for SMoE compression
  ☆222Updated last month
• VITA-Group / Q-GaLore
  Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.
  ☆201Updated last year
• IST-DASLab / Quartet
  ☆118Updated 3 weeks ago
• AlpinDale / QuIP-for-Llama
  Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees" adapted for Llama models
  ☆41Updated 2 years ago
• tiiuae / onebitllms
  Lightweight toolkit package to train and fine-tune 1.58bit Language models
  ☆110Updated 8 months ago
• snowflakedb / ArcticInference
  ArcticInference: vLLM plugin for high-throughput, low-latency inference
  ☆384Updated this week
• OpenGVLab / EfficientQAT
  [ACL 2025 Main] EfficientQAT: Efficient Quantization-Aware Training for Large Language Models
  ☆326Updated 2 months ago
• ServiceNow / Fast-LLM
  Accelerating your LLM training to full speed! Made with ❤️ by ServiceNow Research
  ☆282Updated last week
• cornserve-ai / cornserve
  Easy, Fast, and Scalable Multimodal AI
  ☆106Updated this week
• rafacelente / bllama
  1.58-bit LLaMa model
  ☆82Updated last year
• Infini-AI-Lab / MagicDec
  [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
  ☆137Updated last year
• NickL77 / BaldEagle
  3x Faster Inference; Unofficial implementation of EAGLE Speculative Decoding
  ☆83Updated 7 months ago
• deepseek-ai / LPLB
  An early research stage expert-parallel load balancer for MoE models based on linear programming.
  ☆495Updated 2 months ago
• Zyphra / tree_attention
  Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters
  ☆131Updated last year
• chu-tianxiang / QuIP-for-all
  QuIP quantization
  ☆61Updated last year
• antimatter15 / reverse-engineering-gemma-3n
  Reverse Engineering Gemma 3n: Google's New Edge-Optimized Language Model
  ☆262Updated 8 months ago