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> |
||
|---|---|---|
| .. | ||
| media | ||
| tech_blog | ||
| .gitkeep | ||
| Best_perf_practice_on_DeepSeek-R1_in_TensorRT-LLM.md | ||
| Falcon180B-H200.md | ||
| H100vsA100.md | ||
| H200launch.md | ||
| quantization-in-TRT-LLM.md | ||
| XQA-kernel.md | ||