text-generation-inference/backends/v3
drbh eecca27113
feat: improve qwen2-vl startup (#2802)
* feat: tokenize each request individually and increase warmup image size

* feat: adjust rotary embed and avoid cuda graphs of size 2 and smaller

* fix: address image resize and rebase changes

* feat: update to run qwen2-vl tests

* fix: tweak param types
2025-01-17 11:50:41 -05:00
..
benches Keeping the benchmark somewhere (#2401) 2024-08-12 15:22:02 +02:00
src feat: improve qwen2-vl startup (#2802) 2025-01-17 11:50:41 -05:00
build.rs Rebase TRT-llm (#2331) 2024-07-31 10:33:10 +02:00
Cargo.toml chore: Update jsonschema to 0.28.0 (#2870) 2025-01-10 15:01:54 +01:00