antgroup / DeepXTraceLinks
DeepXTrace is a lightweight tool for precisely diagnosing slow ranks in DeepEP-based environments.
☆47Updated last week
Alternatives and similar repositories for DeepXTrace
Users that are interested in DeepXTrace are comparing it to the libraries listed below
Sorting:
- DeeperGEMM: crazy optimized version☆70Updated 4 months ago
- A lightweight design for computation-communication overlap.☆161Updated last week
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆60Updated this week
- Automated Parallelization System and Infrastructure for Multiple Ecosystems☆79Updated 9 months ago
- An experimental communicating attention kernel based on DeepEP.☆34Updated last month
- ☆63Updated 4 months ago
- ☆57Updated 8 months ago
- ☆55Updated 3 months ago
- ☆46Updated 8 months ago
- Tile-based language built for AI computation across all scales☆51Updated this week
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆109Updated 4 months ago
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆108Updated 3 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 7 months ago
- ☆98Updated last year
- Triton adapter for Ascend. Mirror of https://gitee.com/ascend/triton-ascend☆70Updated this week
- Aims to implement dual-port and multi-qp solutions in deepEP ibrc transport☆61Updated 4 months ago
- Microsoft Collective Communication Library☆66Updated 9 months ago
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆95Updated 2 months ago
- kvcached: Elastic KV cache for dynamic GPU sharing and efficient multi-LLM inference.☆86Updated this week
- ☆23Updated last week
- ☆50Updated 3 months ago
- Stateful LLM Serving☆81Updated 6 months ago
- ☆94Updated 5 months ago
- Implement Flash Attention using Cute.☆95Updated 8 months ago
- ☆30Updated 2 months ago
- Framework to reduce autotune overhead to zero for well known deployments.☆81Updated last week
- ☆290Updated last week
- Pipeline Parallelism Emulation and Visualization☆65Updated 3 months ago
- High performance Transformer implementation in C++.☆132Updated 7 months ago
- gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token Throttling☆39Updated 3 weeks ago