infinigence / Semi-PDLinks
A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.
☆108Updated 3 months ago
Alternatives and similar repositories for Semi-PD
Users that are interested in Semi-PD are comparing it to the libraries listed below
Sorting:
- A lightweight design for computation-communication overlap.☆165Updated this week
- High performance Transformer implementation in C++.☆132Updated 7 months ago
- ☆84Updated 5 months ago
- DeepSeek-V3/R1 inference performance simulator☆165Updated 5 months ago
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆112Updated last year
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆63Updated last year
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆60Updated this week
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆62Updated last year
- Stateful LLM Serving☆83Updated 6 months ago
- AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…☆263Updated 3 weeks ago
- ☆103Updated 3 months ago
- PyTorch distributed training acceleration framework☆52Updated last month
- ☆98Updated last year
- ☆290Updated last week
- Summary of the Specs of Commonly Used GPUs for Training and Inference of LLM☆63Updated last month
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆109Updated 4 months ago
- ☆150Updated 8 months ago
- DeepXTrace is a lightweight tool for precisely diagnosing slow ranks in DeepEP-based environments.☆47Updated last week
- ☆46Updated 9 months ago
- ☆87Updated this week
- ☆69Updated last year
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆94Updated last week
- ☆120Updated 10 months ago
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆61Updated last year
- Summary of some awesome work for optimizing LLM inference☆104Updated 3 months ago
- DLSlime RDMA Transfer Engine☆48Updated this week
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆56Updated last week
- Fast and memory-efficient exact attention☆93Updated this week
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆70Updated 3 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…☆268Updated 6 months ago