Alternatives and similar repositories for LLMSpeculativeSampling

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

• hemingkx / SpeculativeDecodingPapers
  📰 Must-read papers and blogs on Speculative Decoding ⚡️
  ☆1,040Updated this week
• hemingkx / Spec-Bench
  Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)
  ☆338Updated 7 months ago
• FMInference / H2O
  [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.
  ☆487Updated last year
• THUDM / LongBench
  LongBench v2 and LongBench (ACL 25'&24')
  ☆1,032Updated 10 months ago
• hahnyuan / LLM-Viewer
  Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…
  ☆589Updated last year
• zhuzilin / ring-flash-attention
  Ring attention implementation with flash attention
  ☆923Updated 2 months ago
• FMInference / DejaVu
  ☆348Updated last year
• feifeibear / long-context-attention
  USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference
  ☆605Updated last month
• October2001 / Awesome-KV-Cache-Compression
  📰 Must-read papers on KV Cache Compression (constantly updating 🤗).
  ☆614Updated 2 months ago
• pjlab-sys4nlp / llama-moe
  ⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training (EMNLP 2024)
  ☆996Updated last year
• sgl-project / SpecForge
  Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
  ☆523Updated this week
• alibaba / Megatron-LLaMA
  Best practice for training LLaMA models in Megatron-LM
  ☆661Updated last year
• LLMServe / DistServe
  Disaggregated serving system for Large Language Models (LLMs).
  ☆737Updated 7 months ago
• Zefan-Cai / Awesome-LLM-KV-Cache
  Awesome-LLM-KV-Cache: A curated list of 📙Awesome LLM KV Cache Papers with Codes.
  ☆393Updated 9 months ago
• HArmonizedSS / HASS
  Official Implementation of "Learning Harmonized Representations for Speculative Sampling" (HASS)
  ☆51Updated 8 months ago
• microsoft / MInference
  [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…
  ☆1,163Updated 2 months ago
• alibaba / ChatLearn
  A flexible and efficient training framework for large-scale alignment tasks
  ☆440Updated last month
• hao-ai-lab / LookaheadDecoding
  [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding
  ☆1,307Updated 9 months ago
• alibaba / Pai-Megatron-Patch
  The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.
  ☆1,457Updated 3 weeks ago
• ModelTC / LightCompress
  [EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLM, VLM, and video generation models.
  ☆632Updated 2 weeks ago
• dilab-zju / self-speculative-decoding
  Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**
  ☆212Updated 9 months ago
• horseee / LLM-Pruner
  [NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baich…
  ☆1,083Updated last year
• AIoT-MLSys-Lab / Efficient-LLMs-Survey
  [TMLR 2024] Efficient Large Language Models: A Survey
  ☆1,236Updated 5 months ago
• pprp / Awesome-LLM-Prune
  Awesome list for LLM pruning.
  ☆276Updated last month
• facebookresearch / LLM-QAT
  Code repo for the paper "LLM-QAT Data-Free Quantization Aware Training for Large Language Models"
  ☆323Updated 9 months ago
• princeton-nlp / LLM-Shearing
  [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning
  ☆632Updated last year
• TUDB-Labs / mLoRA
  An Efficient "Factory" to Build Multiple LoRA Adapters
  ☆357Updated 9 months ago
• cli99 / llm-analysis
  Latency and Memory Analysis of Transformer Models for Training and Inference
  ☆466Updated 7 months ago
• mit-han-lab / omniserve
  [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…
  ☆786Updated 9 months ago
• flagos-ai / FlagScale
  FlagScale is a large model toolkit based on open-sourced projects.
  ☆416Updated last week