🚨Come check out our poster at #ICML2025!
QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache
📍 East Exhibition Hall A-B — #E-2608
🗓️ Poster Session 5 | Thu, Jul 17 | 🕓 11:00 AM –1:30 PM
TLDR:
Use a quantized version of the same model as its own draft…
🚨Come check out our poster at #ICML2025!
QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache
📍 East Exhibition Hall A-B — #E-2608
🗓️ Poster Session 5 | Thu, Jul 17 | 🕓 11:00 AM –1:30 PM
TLDR:
Use a quantized version of the same model as its own draft…
74 Followers 617 FollowingExperimenting_&_Learning 🌟 Posts about AI, Semiconductor, Hardware, Sales, Neuroscience, Yoga 🌟 Views are my own 🌟 Be Humble, Be Open, Learn the Unknown
1K Followers 2K FollowingInvesting in public and private companies powering the digitalization of the world's economy | Posts are my own views and is not investment advice
503 Followers 321 FollowingVisiting Researcher at FAIR, Meta and CS PhD student at UT Austin. Previously, SR at Google | Pre-Doctoral Research Fellow at MSR India | CS UG at IIT KGP
18K Followers 808 FollowingReinforcement Learner @periodiclabs. Adjunct Prof at McGill. Ex MSL Meta, DeepMind, Brain, Mila, IIT Bombay. NeurIPS Best Paper
39K Followers 994 FollowingCreator of bitsandbytes.Research Scientist @allen_ai and incoming professor @CarnegieMellon. I blog about deep learning and PhD life at https://t.co/Y78KDJJFE7.
477 Followers 270 FollowingBS+MS @Berkeley_EECS + Math | AI research @berkeley_ai | Nuclear Physics Research @BerkeleyLab | Building hyper-intelligent machines.
1K Followers 973 FollowingIncoming Assistant Professor @UTCompSci, Senior Researcher @togethercompute, PhD @UCBerkeley. Working on building cooler things with fewer cost 😊
14K Followers 3K Followingresearch @MIT_CSAIL @thinkymachines. work on scalable and principled algorithms in #LLM and #MLSys. in open-sourcing I trust 🐳. she/her/hers
No recent Favorites. New Favorites will appear here.