Original · EN · English · detectedLeapQuant: the training-free method to make 8-bit or 4-bit recurrent states work. 📈 Across Qwen, Kimi, and GLM models: • Matches FP32 accuracy • 4.25× faster linear attention kernels • Up to 2× higher inference throughput • Cuts memory by up to 56%
Source checks · not independently reviewed
Linked origin: bsky.app.
No publisher-policy review is recorded here. Unknown does not mean unreliable or fake.
Claim: not fact-checked by this project. Sentiment analysis is not fact-checking.
Account identity and expertise are not independently verified. Likes, followers and reposts measure attention, not truth.