Liquid AI Releases LFM2.5-VL-3B-DSpark: Speculative Decoding for Vision-Language Models With Up to 3.13x Faster Decoding
5 min
Jina AI Releases jina-ocr-v1: A 3.4B MoE Document Parser With Built-In Speculative Decoding for Low-Budget GPUs
5 min1
Shapelearn Qwen 3.8 27B (13.1 GB VRAM)
15 min
To Copy or Not to Copy: Controlling Speculative Decoding via Intrinsic Model Signals
1
How Lossless Is Lossless Speculative Decoding? The Role of Numerical Precision in Orthrus
1
SpecGuard: Inference-Time Backdoor Detection For Free
2
DeepSeek AI Released DeepSeek-V4.1-Flash with 1M Context, FP4 KV Cache, and Cross-Layer Attention Reuse
4 min2
Speculative Decoding in vLLM on AMD GPUs
15 min1
Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training
1
Unlocking Lossless Speedups in LLMs via Discrete Diffusion
ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF — new model trending #3 on Hugging Face
9 min1