Alternatives and similar repositories for SpecForge

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

• kwai / Megatron-Kwai
  [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…
  ☆59Updated 11 months ago
• madsys-dev / deepseekv2-profile
  ☆145Updated 4 months ago
• galeselee / Awesome_LLM_System-PaperList
  Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…
  ☆260Updated 4 months ago
• interestingLSY / swiftLLM
  A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …
  ☆237Updated last month
• fzyzcjy / torch_memory_saver
  Allow torch tensor memory to be released and resumed later
  ☆81Updated 2 weeks ago
• microsoft / vattention
  Dynamic Memory Management for Serving LLMs without PagedAttention
  ☆403Updated last month
• ByteDance-Seed / ByteCheckpoint
  ByteCheckpoint: An Unified Checkpointing Library for LFMs
  ☆226Updated 2 weeks ago
• LoongServe / LoongServe
  ☆107Updated 8 months ago
• fanshiqing / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆134Updated last week
• SiriusNEO / Triton-Puzzles-Lite
  Puzzles for learning Triton, play it with minimal environment configuration!
  ☆435Updated 7 months ago
• mit-han-lab / Quest
  [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference
  ☆306Updated 2 weeks ago
• LLMServe / SwiftTransformer
  High performance Transformer implementation in C++.
  ☆128Updated 6 months ago
• microsoft / sarathi-serve
  A low-latency & high-throughput serving engine for LLMs
  ☆395Updated last month
• LLMServe / DistServe
  Disaggregated serving system for Large Language Models (LLMs).
  ☆645Updated 3 months ago
• infinigence / FlashOverlap
  A lightweight design for computation-communication overlap.
  ☆150Updated last month
• microsoft / nnscaler
  nnScaler: Compiling DNN models for Parallel Training
  ☆114Updated 2 weeks ago
• InternLM / Awesome-LLM-Training-System
  ☆41Updated 11 months ago
• sail-sg / zero-bubble-pipeline-parallelism
  Zero Bubble Pipeline Parallelism
  ☆406Updated 2 months ago
• sgl-project / sgl-learning-materials
  Materials for learning SGLang
  ☆494Updated this week
• microsoft / chunk-attention
  ☆77Updated 3 months ago
• smart-lty / ParallelSpeculativeDecoding
  [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length
  ☆96Updated 3 months ago
• FlagOpen / FlagAttention
  A collection of memory efficient attention operators implemented in the Triton language.
  ☆273Updated last year
• EfficientMoE / MoE-Infinity
  PyTorch library for cost-effective, fast and easy serving of MoE models.
  ☆210Updated 2 weeks ago
• sgl-project / genai-bench
  Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…
  ☆172Updated last week
• 66RING / tiny-flash-attention
  flash attention tutorial written in python, triton, cuda, cutlass
  ☆386Updated 2 months ago
• October2001 / Awesome-KV-Cache-Compression
  📰 Must-read papers on KV Cache Compression (constantly updating 🤗).
  ☆490Updated last month
• hao-ai-lab / vllm-ltr
  [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank
  ☆50Updated 8 months ago
• chenhongyu2048 / LLM-inference-optimization-paper
  Summary of some awesome work for optimizing LLM inference
  ☆85Updated last month
• YaoJiayi / CacheBlend
  ☆123Updated last week
• AlibabaPAI / llumnix
  Efficient and easy multi-instance LLM serving
  ☆449Updated last week