A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.
☆135Dec 25, 2025Updated 9 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:
- Repo for SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting (ISCA25)☆75Apr 25, 2025Updated last year
- A lightweight design for computation-communication overlap.☆248Jan 20, 2026Updated 8 months ago
- ☆46Oct 15, 2025Updated 11 months ago
- High-performance distributed data shuffling (all-to-all) library for MoE training and inference☆127Mar 7, 2026Updated 6 months ago
- KV cache store for distributed LLM inference☆444Sep 16, 2026Updated last week
- 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.
- Efficient and easy multi-instance LLM serving☆561Mar 12, 2026Updated 6 months ago
- ☆65Apr 26, 2025Updated last year
- Materials for learning SGLang☆894Jan 5, 2026Updated 8 months ago
- ☆388Jan 28, 2026Updated 8 months ago
- DeeperGEMM: crazy optimized version☆85May 5, 2025Updated last year
- NVIDIA Inference Xfer Library (NIXL)☆1,276Updated this week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,367Aug 28, 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☆19Mar 4, 2025Updated last year
- 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.
- Perplexity GPU Kernels☆609Nov 7, 2025Updated 10 months ago
- DeepSeek-V3/R1 inference performance simulator☆196Mar 27, 2025Updated last year
- a size profiler for cuda binary☆71Jan 15, 2026Updated 8 months ago
- Disaggregated serving system for Large Language Models (LLMs).☆838Apr 6, 2025Updated last year
- Boosting GPU utilization for LLM serving via dynamic spatial-temporal prefill & decode orchestration☆53Updated this week
- Distributed Compiler and Optimized Parallel Kernels☆1,552Sep 18, 2026Updated last week
- ☆92Oct 17, 2025Updated 11 months ago
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,668Updated this week
- Dynamic Memory Management for Serving LLMs without PagedAttention☆524Aug 24, 2026Updated last month
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- ☆54May 19, 2025Updated last year
- ☆75Mar 26, 2025Updated last year
- ☆136Nov 11, 2024Updated last year
- ☆107Sep 9, 2024Updated 2 years ago
- Accurate, large-scale, and extensible simulator for LLM inference Systems☆685Aug 24, 2026Updated last month
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆205Feb 11, 2026Updated 7 months ago
- [NeurIPS 2025] ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive☆77Aug 8, 2026Updated last month
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆1,355Updated this week
- ☆43Oct 12, 2025Updated 11 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Open ABI and FFI for Machine Learning Systems☆465Updated this week
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,194Updated this week
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆560Updated this week
- ☆356Updated this week
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆12Nov 8, 2024Updated last year
- Injecting Adrenaline into LLM Serving: Boosting Resource Utilization and Throughput via Attention Disaggregation☆42Sep 21, 2026Updated last week
- DeDe (OSDI '25): an optimization framework for large-scale resource allocation☆15May 18, 2026Updated 4 months ago