sgl-project / SpecForgeLinks
Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
☆428Updated this week
Alternatives and similar repositories for SpecForge
Users that are interested in SpecForge are comparing it to the libraries listed below
Sorting:
- Dynamic Memory Management for Serving LLMs without PagedAttention☆426Updated 4 months ago
- Materials for learning SGLang☆615Updated 2 weeks ago
- Disaggregated serving system for Large Language Models (LLMs).☆706Updated 6 months ago
- Zero Bubble Pipeline Parallelism☆432Updated 5 months ago
- Allow torch tensor memory to be released and resumed later☆147Updated last week
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆766Updated 7 months ago
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆562Updated last year
- ☆148Updated 7 months ago
- A low-latency & high-throughput serving engine for LLMs☆425Updated 4 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆338Updated 3 months ago
- Perplexity GPU Kernels☆488Updated 3 weeks ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆576Updated this week
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆275Updated 4 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆281Updated last year
- PyTorch bindings for CUTLASS grouped GEMM.☆154Updated last week
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆320Updated 5 months ago
- ByteCheckpoint: An Unified Checkpointing Library for LFMs☆249Updated 3 months ago
- A throughput-oriented high-performance serving framework for LLMs☆904Updated last month
- Efficient and easy multi-instance LLM serving☆497Updated last month
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆65Updated last year
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆559Updated 2 weeks ago
- ☆304Updated 2 weeks ago
- Puzzles for learning Triton, play it with minimal environment configuration!☆545Updated 3 weeks ago
- FlagScale is a large model toolkit based on open-sourced projects.☆361Updated last week
- Best practices for training DeepSeek, Mixtral, Qwen and other MoE models using Megatron Core.☆108Updated last week
- Distributed Compiler based on Triton for Parallel Systems☆1,173Updated 2 weeks ago
- Pipeline Parallelism Emulation and Visualization☆67Updated 4 months ago
- flash attention tutorial written in python, triton, cuda, cutlass☆428Updated 5 months ago
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆277Updated 7 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆320Updated last year