sgl-project / SpecForgeLinks
Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
☆344Updated 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☆407Updated 3 months ago
- ☆146Updated 6 months ago
- Allow torch tensor memory to be released and resumed later☆118Updated this week
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆543Updated 11 months ago
- A low-latency & high-throughput serving engine for LLMs☆409Updated 3 months ago
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆249Updated 2 months ago
- Materials for learning SGLang☆554Updated this week
- Disaggregated serving system for Large Language Models (LLMs).☆683Updated 4 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆327Updated last month
- Zero Bubble Pipeline Parallelism☆423Updated 3 months ago
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆309Updated 4 months ago
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆61Updated last year
- PyTorch bindings for CUTLASS grouped GEMM.☆138Updated last week
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆556Updated last month
- A collection of memory efficient attention operators implemented in the Triton language.☆278Updated last year
- Perplexity GPU Kernels☆449Updated 3 weeks ago
- ByteCheckpoint: An Unified Checkpointing Library for LFMs☆240Updated last month
- ☆288Updated last week
- Puzzles for learning Triton, play it with minimal environment configuration!☆497Updated 9 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…☆266Updated 5 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆746Updated 5 months ago
- Efficient and easy multi-instance LLM serving☆475Updated 2 weeks ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆319Updated last year
- ☆42Updated last year
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆228Updated last month
- Pipeline Parallelism Emulation and Visualization☆63Updated 2 months ago
- ☆93Updated 5 months ago
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆467Updated last year
- High performance Transformer implementation in C++.☆129Updated 7 months ago
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆523Updated last month