sspec-project / SparseSpecLinks
Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding
☆70Updated 3 weeks ago
Alternatives and similar repositories for SparseSpec
Users that are interested in SparseSpec are comparing it to the libraries listed below
Sorting:
- [NeurIPS'25 Spotlight] Adaptive Attention Sparsity with Hierarchical Top-p Pruning☆79Updated 3 weeks ago
- Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆106Updated 3 months ago
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)☆50Updated last year
- ☆58Updated last year
- DeepSeek-V3.2-Exp DSA Warmup Lightning Indexer training operator based on tilelang☆38Updated last month
- [NeurIPS 2025] ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive☆51Updated 2 weeks ago
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆95Updated last week
- 16-fold memory access reduction with nearly no loss☆109Updated 9 months ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆49Updated 4 months ago
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆59Updated 9 months ago
- [HPCA 2026] A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆71Updated last week
- ☆65Updated 8 months ago
- [COLM 2024] SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models☆25Updated last year
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆66Updated last year
- ☆36Updated 2 months ago
- ☆84Updated 8 months ago
- Building the Virtuous Cycle for AI-driven LLM Systems☆100Updated this week
- ☆52Updated 7 months ago
- Tile-based language built for AI computation across all scales☆106Updated this week
- Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]☆47Updated 9 months ago
- DeeperGEMM: crazy optimized version☆73Updated 7 months ago
- ☆80Updated 2 months ago
- ☆39Updated 4 months ago
- Explore Inter-layer Expert Affinity in MoE Model Inference☆16Updated last year
- Debug print operator for cudagraph debugging☆14Updated last year
- ☆126Updated last year
- Efficient Compute-Communication Overlap for Distributed LLM Inference☆66Updated last month
- Multi-Level Triton Runner supporting Python, IR, PTX, and cubin.☆78Updated 2 weeks ago
- DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit☆87Updated this week
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆33Updated last year