sgl-project / SpecForgeLinks
Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
☆615Updated this week
Alternatives and similar repositories for SpecForge
Users that are interested in SpecForge are comparing it to the libraries listed below
Sorting:
- Disaggregated serving system for Large Language Models (LLMs).☆761Updated 9 months ago
- Zero Bubble Pipeline Parallelism☆445Updated 8 months ago
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆602Updated last year
- Materials for learning SGLang☆714Updated this week
- Dynamic Memory Management for Serving LLMs without PagedAttention☆454Updated 7 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆621Updated 2 weeks ago
- Allow torch tensor memory to be released and resumed later☆196Updated last month
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆347Updated 8 months ago
- A low-latency & high-throughput serving engine for LLMs☆462Updated 2 months ago
- ☆153Updated 10 months ago
- A throughput-oriented high-performance serving framework for LLMs☆936Updated 2 months ago
- Efficient and easy multi-instance LLM serving☆520Updated 4 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆362Updated 5 months ago
- FlagScale is a large model toolkit based on open-sourced projects.☆431Updated this week
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆303Updated 7 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆801Updated 10 months ago
- LLM training technologies developed by kwai☆68Updated last month
- ByteCheckpoint: An Unified Checkpointing Library for LFMs☆256Updated last month
- PyTorch bindings for CUTLASS grouped GEMM.☆180Updated 3 weeks ago
- Perplexity GPU Kernels☆548Updated 2 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆287Updated last year
- Accelerating MoE with IO and Tile-aware Optimizations☆522Updated this week
- Distributed Compiler based on Triton for Parallel Systems☆1,307Updated last week
- ☆337Updated this week
- Puzzles for learning Triton, play it with minimal environment configuration!☆584Updated last week
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆282Updated 10 months ago
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆250Updated 3 weeks ago
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆631Updated 3 months ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆269Updated 2 months ago
- ☆352Updated last year