speculative decoding
3 articles tagged with speculative decoding
Liquid AI Ships DSpark Draft Models, Cutting LFM2.5 Inference Latency Up to 3.18x on GPU
Liquid AI released DSpark draft model checkpoints for three LFM2.5 models, enabling speculative decoding that speeds up inference by up to 3.18x on H100 GPUs and 2.87x on-device, with day-one support for llama.cpp and SGLang.
DeepSeek Releases DeepSeek-V4-Pro-0813, a 1.7T-Parameter Model with DSpark Speculative Decoding
DeepSeek has released DeepSeek-V4-Pro-0813, a 1.7-trillion-parameter model that supersedes the DeepSeek-V4-Pro preview. The model adds a DSpark speculative decoding module and posts measurable gains on agentic and coding benchmarks, according to DeepSeek's technical report.
DeepSeek Releases V4-Flash-0731, a 304B-Parameter Model Claiming to Beat Its Own Pro Preview on Agentic Benchmarks
DeepSeek has released DeepSeek-V4-Flash-0731, a 304-billion-parameter model that supersedes its earlier preview version with what the company describes as substantially enhanced agentic capabilities. According to DeepSeek's technical report, the model outperforms the larger DeepSeek-V4-Pro (Preview) on several coding and agent benchmarks despite a far smaller activated parameter count.