FANCD2
PulseAugur coverage of FANCD2 — every cluster mentioning FANCD2 across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New FP4 attention kernels boost B300 performance by 1.69x
A new set of FP4 attention kernels has been developed for the B300, offering a significant speedup of up to 1.69x compared to FA4. This advancement aims to improve the performance of local large language models.
-
Jet-Long method boosts LLM long-context performance without retraining
Researchers have introduced Jet-Long, a novel method for extending the context window of large language models without requiring retraining. This tuning-free, zero-shot approach dynamically adjusts rescaling factors to …
-
New speculative decoding methods boost LLM inference speed and safety
Researchers are developing advanced speculative decoding techniques to accelerate large language model inference. HyperDFlash optimizes decoding for DeepSeek-V4's multi-hyper-connection architecture, improving draft acc…