Alert button
Picture for Charlie Blake

Charlie Blake

Alert button

SparQ Attention: Bandwidth-Efficient LLM Inference

Dec 08, 2023
Luka Ribar, Ivan Chelombiev, Luke Hudlass-Galley, Charlie Blake, Carlo Luschi, Douglas Orr

Viaarxiv icon

Training and inference of large language models using 8-bit floating point

Sep 29, 2023
Sergio P. Perez, Yan Zhang, James Briggs, Charlie Blake, Josh Levy-Kramer, Paul Balanca, Carlo Luschi, Stephen Barlow, Andrew William Fitzgibbon

Viaarxiv icon

Unit Scaling: Out-of-the-Box Low-Precision Training

Mar 20, 2023
Charlie Blake, Douglas Orr, Carlo Luschi

Figure 1 for Unit Scaling: Out-of-the-Box Low-Precision Training
Figure 2 for Unit Scaling: Out-of-the-Box Low-Precision Training
Figure 3 for Unit Scaling: Out-of-the-Box Low-Precision Training
Figure 4 for Unit Scaling: Out-of-the-Box Low-Precision Training
Viaarxiv icon

Snowflake: Scaling GNNs to High-Dimensional Continuous Control via Parameter Freezing

Mar 01, 2021
Charlie Blake, Vitaly Kurin, Maximilian Igl, Shimon Whiteson

Figure 1 for Snowflake: Scaling GNNs to High-Dimensional Continuous Control via Parameter Freezing
Figure 2 for Snowflake: Scaling GNNs to High-Dimensional Continuous Control via Parameter Freezing
Figure 3 for Snowflake: Scaling GNNs to High-Dimensional Continuous Control via Parameter Freezing
Figure 4 for Snowflake: Scaling GNNs to High-Dimensional Continuous Control via Parameter Freezing
Viaarxiv icon

The Winnability of Klondike and Many Other Single-Player Card Games

Jun 28, 2019
Charlie Blake, Ian P. Gent

Figure 1 for The Winnability of Klondike and Many Other Single-Player Card Games
Figure 2 for The Winnability of Klondike and Many Other Single-Player Card Games
Figure 3 for The Winnability of Klondike and Many Other Single-Player Card Games
Figure 4 for The Winnability of Klondike and Many Other Single-Player Card Games
Viaarxiv icon