infinigence / FlashOverlapLinks
A lightweight design for computation-communication overlap.
☆181Updated 2 weeks ago
Alternatives and similar repositories for FlashOverlap
Users that are interested in FlashOverlap are comparing it to the libraries listed below
Sorting:
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆138Updated last month
- High performance Transformer implementation in C++.☆138Updated 9 months ago
- ☆100Updated last year
- nnScaler: Compiling DNN models for Parallel Training☆118Updated last month
- ☆107Updated 5 months ago
- ☆90Updated 6 months ago
- ☆141Updated 9 months ago
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆113Updated 5 months ago
- ☆307Updated 3 weeks ago
- ☆74Updated last week
- DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit☆70Updated this week
- [NeurIPS 2025] ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive☆45Updated last month
- DeepSeek-V3/R1 inference performance simulator☆170Updated 6 months ago
- We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …☆186Updated 8 months ago
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆60Updated 2 weeks ago
- Distributed MoE in a Single Kernel [NeurIPS '25]☆89Updated 3 weeks ago
- Automated Parallelization System and Infrastructure for Multiple Ecosystems☆80Updated 11 months ago
- DeeperGEMM: crazy optimized version☆72Updated 5 months ago
- ☆65Updated 5 months ago
- ☆83Updated 2 years ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆121Updated 5 months ago
- ☆124Updated 11 months ago
- Sequence-level 1F1B schedule for LLMs.☆32Updated last month
- Chimera: bidirectional pipeline parallelism for efficiently training large-scale models.☆67Updated 7 months ago
- ☆150Updated 5 months ago
- Implement Flash Attention using Cute.☆96Updated 10 months ago
- Examples of CUDA implementations by Cutlass CuTe☆241Updated 3 months ago
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆63Updated last month
- ☆61Updated 4 months ago
- NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process com…☆351Updated last week