Alternatives and similar repositories for zeus:

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

• ml-energy / leaderboard
  How much energy do GenAI models consume?
  ☆41Updated 4 months ago
• microsoft / vidur
  A large-scale simulation framework for LLM inference
  ☆325Updated 3 months ago
• project-etalon / etalon
  LLM Serving Performance Evaluation Harness
  ☆68Updated this week
• ScalingIntelligence / KernelBench
  KernelBench: Can LLMs Write GPU Kernels? - Benchmark with Torch -> CUDA problems
  ☆183Updated this week
• HPMLL / BurstGPT
  A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems
  ☆145Updated 4 months ago
• mobiusml / gemlite
  Fast low-bit matmul kernels in Triton
  ☆236Updated this week
• HanGuo97 / flute
  Fast Matrix Multiplications for Lookup Table-Quantized LLMs
  ☆229Updated this week
• Azure / msccl
  Microsoft Collective Communication Library
  ☆62Updated 2 months ago
• TorchMoE / MoE-Infinity
  PyTorch library for cost-effective, fast and easy serving of MoE models.
  ☆132Updated this week
• SymbioticLab / Oobleck
  A resilient distributed training framework
  ☆88Updated 10 months ago
• cchan / tccl
  extensible collectives library in triton
  ☆83Updated 4 months ago
• microsoft / vattention
  Dynamic Memory Management for Serving LLMs without PagedAttention
  ☆290Updated this week
• microsoft / sarathi-serve
  A low-latency & high-throughput serving engine for LLMs
  ☆312Updated 3 weeks ago
• facebookresearch / ACT
  ACT An Architectural Carbon Modeling Tool for Designing Sustainable Computer Systems
  ☆36Updated this week
• Hsword / SpotServe
  SpotServe: Serving Generative Large Language Models on Preemptible Instances
  ☆112Updated 11 months ago
• tyler-griggs / melange-release
  ☆43Updated 7 months ago
• LLMServe / SwiftTransformer
  High performance Transformer implementation in C++.
  ☆102Updated last month
• pytorch / torchsnapshot
  A performant, memory-efficient checkpointing library for PyTorch applications, designed with large, complex distributed workloads in mind…
  ☆154Updated 2 months ago
• microsoft / SuperScaler
  An experimental parallel training platform
  ☆54Updated 10 months ago
• facebookresearch / param
  PArametrized Recommendation and Ai Model benchmark is a repository for development of numerous uBenchmarks as well as end to end nets for…
  ☆128Updated this week
• SamsungLabs / Metis
  [ATC '24] Metis: Fast automatic distributed training on heterogeneous GPUs (https://www.usenix.org/conference/atc24/presentation/um)
  ☆25Updated 3 months ago
• AlibabaResearch / flash-llm
  Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity
  ☆199Updated last year
• facebookresearch / HolisticTraceAnalysis
  A library to analyze PyTorch traces.
  ☆332Updated last week
• efeslab / fiddler
  [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration
  ☆193Updated 3 months ago
• facebookresearch / CarbonExplorer
  Carbon Explorer helps evaluating solutions make datacenters operate on renewable energy.
  ☆71Updated 3 months ago
• microsoft / ParrotServe
  [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable
  ☆143Updated 4 months ago
• AlibabaPAI / llumnix
  Efficient and easy multi-instance LLM serving
  ☆295Updated this week
• Deep-Learning-Profiling-Tools / triton-viz
  ☆179Updated last week
• Dao-AILab / fast-hadamard-transform
  Fast Hadamard transform in CUDA, with a PyTorch interface
  ☆143Updated 8 months ago
• pytorch-labs / float8_experimental
  This repository contains the experimental PyTorch native float8 training UX
  ☆221Updated 6 months ago