HydraQYH / expert_specialization_moeLinks
Expert Specialization MoE Solution based on CUTLASS
☆24Updated 3 weeks ago
Alternatives and similar repositories for expert_specialization_moe
Users that are interested in expert_specialization_moe are comparing it to the libraries listed below
Sorting:
- ☆41Updated 3 months ago
- ☆32Updated 6 months ago
- DeeperGEMM: crazy optimized version☆74Updated 8 months ago
- ☆39Updated 5 months ago
- ☆65Updated 8 months ago
- Nex Venus Communication Library☆70Updated 2 months ago
- Distributed MoE in a Single Kernel [NeurIPS '25]☆178Updated this week
- Efficient Long-context Language Model Training by Core Attention Disaggregation☆75Updated 2 weeks ago
- Utility scripts for PyTorch (e.g. Make Perfetto show some disappearing kernels, Memory profiler that understands more low-level allocatio…☆80Updated 4 months ago
- An experimental communicating attention kernel based on DeepEP.☆35Updated 5 months ago
- Tile-based language built for AI computation across all scales☆115Updated 3 weeks ago
- ☆52Updated 7 months ago
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆153Updated 3 months ago
- Debug print operator for cudagraph debugging☆14Updated last year
- ☆45Updated last year
- A lightweight design for computation-communication overlap.☆209Updated 3 weeks ago
- [HPCA 2026] A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆76Updated 3 weeks ago
- DeepSeek-V3.2-Exp DSA Warmup Lightning Indexer training operator based on tilelang☆41Updated last month
- [NeurIPS 2025] ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive☆62Updated last month
- ☆39Updated last month
- a simple API to use CUPTI☆11Updated 4 months ago
- High-performance distributed data shuffling (all-to-all) library for MoE training and inference☆106Updated 2 weeks ago
- 16-fold memory access reduction with nearly no loss☆109Updated 9 months ago
- ☆35Updated 10 months ago
- [NeurIPS'25 Spotlight] Adaptive Attention Sparsity with Hierarchical Top-p Pruning☆83Updated last month
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆159Updated 2 months ago
- Estimate MFU for DeepSeekV3☆26Updated last year
- Implement Flash Attention using Cute.☆100Updated last year
- DeepXTrace is a lightweight tool for precisely diagnosing slow ranks in DeepEP-based environments.☆86Updated 3 weeks ago
- ☆126Updated 4 months ago