infinigence / FlashOverlapLinks
A lightweight design for computation-communication overlap.
☆154Updated last month
Alternatives and similar repositories for FlashOverlap
Users that are interested in FlashOverlap are comparing it to the libraries listed below
Sorting:
- High performance Transformer implementation in C++.☆128Updated 6 months ago
- ☆89Updated 2 months ago
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆103Updated 2 months ago
- ☆96Updated 10 months ago
- nnScaler: Compiling DNN models for Parallel Training☆114Updated this week
- ☆109Updated 8 months ago
- ☆81Updated 4 months ago
- We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …☆183Updated 6 months ago
- ☆126Updated 2 months ago
- ☆101Updated 7 months ago
- ☆60Updated 3 months ago
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆56Updated last week
- DeepSeek-V3/R1 inference performance simulator☆156Updated 4 months ago
- DeeperGEMM: crazy optimized version☆70Updated 2 months ago
- ☆128Updated 7 months ago
- ☆150Updated last year
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆91Updated 2 months ago
- Implement Flash Attention using Cute.☆92Updated 7 months ago
- Automated Parallelization System and Infrastructure for Multiple Ecosystems☆79Updated 8 months ago
- ☆65Updated last year
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆48Updated last week
- Examples of CUDA implementations by Cutlass CuTe☆211Updated last month
- ☆227Updated last year
- ☆24Updated last week
- ☆80Updated 2 years ago
- gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token Throttling☆36Updated this week
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆216Updated last year
- Chimera: bidirectional pipeline parallelism for efficiently training large-scale models.☆67Updated 4 months ago
- Pipeline Parallelism Emulation and Visualization☆54Updated last month
- Sequence-level 1F1B schedule for LLMs.☆29Updated last month