A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.
☆142Dec 25, 2025Updated 10 months ago
Alternatives and similar repositories for Semi-PD
Users that are interested in Semi-PD are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A lightweight design for computation-communication overlap.☆252Jan 20, 2026Updated 9 months ago
- Repo for SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting (ISCA25)☆75Apr 25, 2025Updated last year
- ☆46Oct 15, 2025Updated last year
- ☆14Sep 22, 2025Updated last year
- Disaggregated serving system for Large Language Models (LLMs).☆847Apr 6, 2025Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- High-performance distributed data shuffling (all-to-all) library for MoE training and inference☆127Mar 7, 2026Updated 8 months ago
- Efficient and easy multi-instance LLM serving☆560Mar 12, 2026Updated 7 months ago
- KV cache store for distributed LLM inference☆451Sep 16, 2026Updated last month
- Materials for learning SGLang☆899Jan 5, 2026Updated 10 months ago
- DeeperGEMM: crazy optimized version☆85May 5, 2025Updated last year
- Dynamic Memory Management for Serving LLMs without PagedAttention☆526Aug 24, 2026Updated 2 months ago
- ☆392Jan 28, 2026Updated 9 months ago
- High performance Transformer implementation in C++.☆166Jan 18, 2025Updated last year
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,376Aug 28, 2025Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Perplexity GPU Kernels☆614Nov 7, 2025Updated last year
- NVIDIA Inference Xfer Library (NIXL)☆1,359Updated this week
- A throughput-oriented high-performance serving framework for LLMs☆976Mar 29, 2026Updated 7 months ago
- Distributed Compiler and Optimized Parallel Kernels☆1,577Sep 18, 2026Updated last month
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆208Feb 11, 2026Updated 8 months ago
- ☆65Apr 26, 2025Updated last year
- An experimental communicating attention kernel based on DeepEP.☆34Jul 29, 2025Updated last year
- DuoDecoding: Hardware-aware Heterogeneous Speculative Decoding with Dynamic Multi-Sequence Drafting☆20Mar 4, 2025Updated last year
- GLake: optimizing GPU memory management and IO transmission.☆502Mar 24, 2025Updated last year
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- ☆136Nov 11, 2024Updated last year
- ☆553Aug 27, 2026Updated 2 months ago
- ☆381Updated this week
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,265Updated this week
- DeepSeek-V3/R1 inference performance simulator☆199Mar 27, 2025Updated last year
- FlashTile is a CUDA Tile IR compiler that is compatible with NVIDIA's tileiras, targeting SM70 through SM121 NVIDIA GPUs.☆61Feb 6, 2026Updated 9 months ago
- A low-latency & high-throughput serving engine for LLMs☆535Jan 8, 2026Updated 9 months ago
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆1,394Updated this week
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆691Sep 11, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆54May 19, 2025Updated last year
- a size profiler for cuda binary☆74Oct 3, 2026Updated last month
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,994Updated this week
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆570Updated this week
- ☆92Oct 17, 2025Updated last year
- Draft-Target Disaggregation LLM Serving System via Parallel Speculative Decoding.☆224Mar 18, 2026Updated 7 months ago
- Accurate, large-scale, and extensible simulator for LLM inference Systems☆720Aug 24, 2026Updated 2 months ago