infinigence / Semi-PDLinks
A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.
☆113Updated 5 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.☆181Updated 2 weeks ago
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆138Updated last month
- High performance Transformer implementation in C++.☆138Updated 9 months ago
- DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit☆70Updated this week
- DeepSeek-V3/R1 inference performance simulator☆170Updated 6 months ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆62Updated last year
- ☆90Updated 6 months ago
- ☆307Updated 3 weeks ago
- ☆100Updated last year
- AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…☆265Updated 2 months ago
- Stateful LLM Serving☆87Updated 7 months ago
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆115Updated last year
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆121Updated 5 months ago
- ☆46Updated 10 months ago
- ☆91Updated last week
- ☆107Updated 5 months ago
- ☆74Updated last week
- Summary of the Specs of Commonly Used GPUs for Training and Inference of LLM☆63Updated 2 months ago
- TVM FFI☆79Updated this week
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆62Updated last year
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆63Updated last month
- PyTorch distributed training acceleration framework☆53Updated 2 months ago
- nnScaler: Compiling DNN models for Parallel Training☆118Updated last month
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆65Updated last year
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆94Updated last month
- ☆124Updated 11 months ago
- ☆150Updated 9 months ago
- Automated Parallelization System and Infrastructure for Multiple Ecosystems☆80Updated 11 months ago
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆75Updated 4 months ago
- ☆96Updated 6 months ago