Topics
Results for “decoding”
34 results
- HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF — Hugging Face Models · Seen
- MMFlash: Faster Speculative Decoding for Vision-Language Models — Hugging Face Papers · Seen · 35 points
- tencent/Qwen3.8-27B-DSpine-b16 — Hugging Face Models · Seen
- Six Serving Engines, One 8 GB GPU: Gemma 4 E2B on an RTX 3050 — DEV Community · Seen
- Decoding REXPaint Files in Odin — Hacker News · Seen · 22 points
- Fix an agent's charset decoding of fetched web pages — Agent Use Cases · Seen
- Rethinking in Spikes: Mitigating Hallucinations in MDLMs with Step-Aware Decoding — arXiv AI Papers · Seen
- SpecPilot: Autonomous Algorithm Discovery and Systems Optimization for Speculative Decoding — Hugging Face Papers · Seen · 20 points
- ChainFlow: Few-Step Latent Flow Matching for Speculative Decoding — arXiv AI Papers · Seen
- I Retested My MoE Offloading Benchmarks. Some of My Conclusions Changed. — DEV Community · Seen
- nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB — Hugging Face Models · Seen
- Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding — Hugging Face Papers · Seen · 18 points
- Run AI Models for Edge Application Development with Just a Few Commands — NVIDIA Developer Blog · Seen
- unsloth/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF — Hugging Face Models · Seen
- 3 Ways to Boost MoE Inference on NVIDIA DGX Spark — NVIDIA Developer Blog · Seen
- KRAFTON/Raon-1-mini-preview — Hugging Face Models · Seen
- Distributed LLM Inference via Communication-Efficient Speculative Decoding — arXiv AI Papers · Seen
- Fixing Tool-Call Accuracy in vLLM — Hacker News · Seen · 172 points
- ProtoEEG: Structured Prototype Alignment for EEG Visual Decoding — arXiv AI Papers · Seen
- KDHNet: A Knowledge-Driven Hybrid Network for Limited-Calibration SSVEP Decoding — arXiv AI Papers · Seen
- TraceQuery: learning what to recompute from full-denoising trajectory in diffusion language models — arXiv AI Papers · Seen
- ttindall/Qwen3.8-27B-Defiance-Uncensored-MTP-GGUF — Hugging Face Models · Seen
- nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4 — Hugging Face Models · Seen
- DLite: History-free Speculative Decoding for Agentic AI — Hugging Face Papers · Seen · 26 points
- nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2 — Hugging Face Models · Seen
- Factorization-Guided Training and Inference for Diffusion-Drafted Speculative Decoding — arXiv AI Papers · Seen
- PolyGraph: Plan-Buffered CUDA Graphs for Adaptive Speculative Decoding — arXiv AI Papers · Seen
- Why Is Speculative Decoding Fast? — Hacker News · Seen · 44 points
- On the SPOT: Enhancing Speculative Decoding for Diffusion Language Models via Commit-Order Prediction — arXiv AI Papers · Seen
- Each step of decoding a PNG (2022) — Hacker News · Seen · 38 points
- autotrust/GLM5.3-Flash-E192-DGX-Spark — Hugging Face Models · Seen
- Semantic Alignment of EEG and Text: A Contrastive Learning Framework for Decoding Imagined Speech — arXiv AI Papers · Seen
- Joint Subspace Sparse Attention for Efficient Long-Context Decoding — arXiv AI Papers · Seen
- ReplaySSM: Rethinking State Storage for Faster Hybrid-Model Decoding — NVIDIA Developer Blog · Seen