Alternatives and similar repositories for melange-release:

Users that are interested in melange-release are comparing it to the libraries listed below

• project-etalon / etalon
  LLM Serving Performance Evaluation Harness
  ☆66Updated 5 months ago
• Infini-AI-Lab / MagicDec
  [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
  ☆107Updated 2 months ago
• zhengzangw / Sequence-Scheduling
  PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".
  ☆81Updated last year
• Hsword / SpotServe
  SpotServe: Serving Generative Large Language Models on Preemptible Instances
  ☆111Updated 11 months ago
• hao-ai-lab / MuxServe
  ☆50Updated 8 months ago
• WukLab / preble
  Stateful LLM Serving
  ☆46Updated 6 months ago
• microsoft / ParrotServe
  [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable
  ☆143Updated 4 months ago
• SymbioticLab / Oobleck
  A resilient distributed training framework
  ☆88Updated 10 months ago
• UChi-JCL / CacheGen
  ☆87Updated 4 months ago
• YaoJiayi / CacheBlend
  ☆75Updated last month
• hao-ai-lab / vllm-ltr
  [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank
  ☆37Updated 3 months ago
• efeslab / fiddler
  [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration
  ☆192Updated 2 months ago
• LoongServe / LoongServe
  ☆83Updated 3 months ago
• yale-sys / prompt-cache
  Modular and structured prompt caching for low-latency LLM inference
  ☆87Updated 3 months ago
• opengear-project / GEAR
  GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM
  ☆157Updated 7 months ago
• microsoft / sarathi-serve
  A low-latency & high-throughput serving engine for LLMs
  ☆308Updated 2 weeks ago
• TorchMoE / MoE-Infinity
  PyTorch library for cost-effective, fast and easy serving of MoE models.
  ☆128Updated this week
• MDK8888 / vllmini
  A minimal implementation of vllm.
  ☆33Updated 6 months ago
• amazon-science / piperag
  PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design (KDD 2025)
  ☆17Updated 8 months ago
• IST-DASLab / Sparse-Marlin
  Boosting 4-bit inference kernels with 2:4 Sparsity
  ☆64Updated 5 months ago
• LLMServe / SwiftTransformer
  High performance Transformer implementation in C++.
  ☆101Updated 3 weeks ago
• tonyzhao-jt / LLM-PQ
  Official Repo for "LLM-PQ: Serving LLM on Heterogeneous Clusters with Phase-Aware Partition and Adaptive Quantization"
  ☆28Updated 11 months ago
• microsoft / chunk-attention
  ☆62Updated 2 months ago
• thu-pacman / FasterMoE
  ☆75Updated 2 years ago
• flexflow / flexflow-serve
  FlexFlow Serve: Low-Latency, High-Performance LLM Serving
  ☆17Updated this week
• andy-yang-1 / DoubleSparse
  16-fold memory access reduction with nearly no loss
  ☆76Updated 3 months ago
• microsoft / vidur
  A large-scale simulation framework for LLM inference
  ☆321Updated 2 months ago
• MoE-Inf / awesome-moe-inference
  Curated collection of papers in MoE model inference
  ☆59Updated this week
• IsaacRe / vllm-kvcompress
  KV cache compression for high-throughput LLM inference
  ☆114Updated last week
• dywsjtu / apparate
  Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]
  ☆22Updated 2 months ago