hao-ai-lab / DistCALinks
Efficient Long-context Language Model Training by Core Attention Disaggregation
☆55Updated this week
Alternatives and similar repositories for DistCA
Users that are interested in DistCA are comparing it to the libraries listed below
Sorting:
- ☆115Updated 7 months ago
- ☆52Updated 7 months ago
- ☆39Updated 4 months ago
- [NeurIPS 2025] Scaling Speculative Decoding with Lookahead Reasoning☆56Updated last month
- DeeperGEMM: crazy optimized version☆73Updated 7 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆51Updated 5 months ago
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆107Updated last month
- ☆207Updated last month
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆135Updated last year
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆52Updated last year
- Vortex: A Flexible and Efficient Sparse Attention Framework☆43Updated 3 weeks ago
- Debug print operator for cudagraph debugging☆14Updated last year
- Fast and memory-efficient exact attention☆14Updated last week
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆126Updated 5 months ago
- ☆65Updated 7 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆159Updated 2 months ago
- ☆31Updated 5 months ago
- Quantized Attention on GPU☆44Updated last year
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆114Updated 2 weeks ago
- Autonomous GPU Kernel Generation via Deep Agents☆187Updated this week
- An experimental communicating attention kernel based on DeepEP.☆35Updated 4 months ago
- DeepSeek-V3.2-Exp DSA Warmup Lightning Indexer training operator based on tilelang☆37Updated last month
- A NCCL extension library, designed to efficiently offload GPU memory allocated by the NCCL communication library.☆66Updated last week
- Estimate MFU for DeepSeekV3☆26Updated 11 months ago
- 16-fold memory access reduction with nearly no loss☆109Updated 8 months ago
- Accelerating MoE with IO and Tile-aware Optimizations☆351Updated this week
- Efficient Compute-Communication Overlap for Distributed LLM Inference☆66Updated last month
- ☆133Updated 6 months ago
- Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding☆62Updated 3 weeks ago
- Triton-based Symmetric Memory operators and examples☆67Updated 2 months ago