mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
* add mtp tech blog. Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com> * update figure size. Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com> * update the figure caption style and add some code/pr links. Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com> * fix figure captions. Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com> * fix figure size and perf data. Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com> * fix. Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com> * fix. Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com> * fix. Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com> * fix. Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com> * fix based on comments Signed-off-by: Yue Weng <25103990+yweng0828@users.noreply.github.com> * fix figure links. Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com> --------- Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com> Signed-off-by: Yue Weng <25103990+yweng0828@users.noreply.github.com> Co-authored-by: Yue Weng <25103990+yweng0828@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| blog1_Pushing_Latency_Boundaries_Optimizing_DeepSeek-R1_Performance_on_NVIDIA_B200_GPUs.md | ||
| blog2_DeepSeek_R1_MTP_Implementation_and_Optimization.md | ||