sgl-project / SpecForgeLinks
Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
☆404Updated 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☆418Updated 3 months ago
- Disaggregated serving system for Large Language Models (LLMs).☆691Updated 5 months ago
- Materials for learning SGLang☆579Updated 3 weeks ago
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆556Updated last year
- Allow torch tensor memory to be released and resumed later☆135Updated 2 weeks ago
- A low-latency & high-throughput serving engine for LLMs☆418Updated 3 months ago
- Zero Bubble Pipeline Parallelism☆427Updated 4 months ago
- ☆147Updated 6 months ago
- Perplexity GPU Kernels☆469Updated last week
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆264Updated 3 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆335Updated 2 months ago
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆313Updated 5 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆756Updated 6 months ago
- Efficient and easy multi-instance LLM serving☆487Updated 3 weeks ago
- ☆295Updated this week
- Puzzles for learning Triton, play it with minimal environment configuration!☆518Updated this week
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆270Updated 6 months ago
- ByteCheckpoint: An Unified Checkpointing Library for LFMs☆245Updated 2 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆569Updated last week
- A collection of memory efficient attention operators implemented in the Triton language.☆279Updated last year
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆63Updated last year
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆540Updated last month
- flash attention tutorial written in python, triton, cuda, cutlass☆420Updated 4 months ago
- Distributed Compiler based on Triton for Parallel Systems☆1,137Updated this week
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆238Updated 2 months ago
- Latency and Memory Analysis of Transformer Models for Training and Inference☆455Updated 5 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆320Updated last year
- FlagScale is a large model toolkit based on open-sourced projects.☆354Updated this week
- PyTorch bindings for CUTLASS grouped GEMM.☆151Updated 3 weeks ago
- ☆42Updated last year