mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
* add best perf practice on DSR1 Signed-off-by: Jun Yang <143764042+juney-nvidia@users.noreply.github.com> * add ds-r1 min latency tech blog Signed-off-by: Jun Yang <143764042+juney-nvidia@users.noreply.github.com> * rm redundant doc Signed-off-by: Jun Yang <143764042+juney-nvidia@users.noreply.github.com> * refine table content Signed-off-by: Jun Yang <143764042+juney-nvidia@users.noreply.github.com> * refine table content Signed-off-by: Jun Yang <143764042+juney-nvidia@users.noreply.github.com> * relative path for images Signed-off-by: Jun Yang <143764042+juney-nvidia@users.noreply.github.com> * refine precommit Signed-off-by: Jun Yang <143764042+juney-nvidia@users.noreply.github.com> * pr4280 is merged Signed-off-by: Jun Yang <143764042+juney-nvidia@users.noreply.github.com> --------- Signed-off-by: Jun Yang <143764042+juney-nvidia@users.noreply.github.com>
32 KiB
640x480px
32 KiB
640x480px