Nicolas Patry 0c9b6cdd76 Choosing input/total tokens automatically based on available VRAM? (#2673) ... * Choosing input/total tokens automatically based on available VRAM? * Update doc. * Remove generated files. * Trying to fix non chunking targets. * Attempt #2 * fix. * QuantLinear is rocm compatible. * Much simpler logic after the overhead. * Updating logic + non flash. * Revert doc text. * Simple updates. * Fix integration mt0 (transformers update).		2024-10-28 04:59:49 +01:00
..
benches	Keeping the benchmark somewhere (#2401)	2024-08-12 15:22:02 +02:00
src	Choosing input/total tokens automatically based on available VRAM? (#2673)	2024-10-28 04:59:49 +01:00
Cargo.toml	fix: bump minijinja version and add test for llama 3.1 tools (#2463)	2024-08-27 13:31:08 -04:00
build.rs	Rebase TRT-llm (#2331)	2024-07-31 10:33:10 +02:00