sunkx109 / GPUs-SpecsLinks
Summary of the Specs of Commonly Used GPUs for Training and Inference of LLM
☆63Updated 3 months ago
Alternatives and similar repositories for GPUs-Specs
Users that are interested in GPUs-Specs are comparing it to the libraries listed below
Sorting:
- DeepSeek-V3/R1 inference performance simulator☆168Updated 7 months ago
- ☆90Updated 7 months ago
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆114Updated 5 months ago
- A lightweight design for computation-communication overlap.☆183Updated last month
- Summary of some awesome work for optimizing LLM inference☆135Updated 2 weeks ago
- High performance Transformer implementation in C++.☆141Updated 9 months ago
- DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit☆78Updated this week
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆142Updated last month
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆119Updated last year
- gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token Throttling☆43Updated last month
- Tile-based language built for AI computation across all scales☆78Updated this week
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆278Updated 8 months ago
- Open ABI and FFI for Machine Learning Systems☆167Updated this week
- A baseline repository of Auto-Parallelism in Training Neural Networks☆147Updated 3 years ago
- ☆110Updated 6 months ago
- Repo for SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting (ISCA25)☆67Updated 6 months ago
- Examples of CUDA implementations by Cutlass CuTe☆247Updated 4 months ago
- ☆79Updated 3 years ago
- ☆152Updated 10 months ago
- Multi-Level Triton Runner supporting Python, IR, PTX, and cubin.☆76Updated this week
- nnScaler: Compiling DNN models for Parallel Training☆118Updated last month
- From Minimal GEMM to Everything☆73Updated this week
- ☆40Updated last year
- ☆102Updated last year
- llm theoretical performance analysis tools and support params, flops, memory and latency analysis.☆112Updated 4 months ago
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆66Updated last year
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆63Updated last year
- ☆63Updated 5 months ago
- Canvas: End-to-End Kernel Architecture Search in Neural Networks☆26Updated 11 months ago
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆62Updated last year