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> |
||
|---|---|---|
| .. | ||
| .gitkeep | ||
| Falcon180B-H200_acc.png | ||
| Falcon180B-H200_DecvOct.png | ||
| Falcon180B-H200_H200vA100.png | ||
| Falcon180B-H200_tps.png | ||
| H200launch_H200vsH100_tps.png | ||
| H200launch_tps.png | ||
| moe_structure.png | ||
| tech_blog1_fuse_a_gemm.png | ||
| tech_blog1_model_details.png | ||
| tech_blog1_model_overview.png | ||
| tech_blog1_router_gemm.png | ||
| tech_blog1_sparse_exp_as_a_gemm.png | ||
| tech_blog2_acc_relaxed_acceptance.png | ||
| tech_blog2_mtp_eagle.png | ||
| tech_blog2_mtp_modules.png | ||
| tech_blog2_mtp_vanilla.png | ||
| tech_blog2_overall_workflow.png | ||
| tech_blog2_perf_and_ar.png | ||
| tech_blog2_relaxed_acceptance.png | ||
| tech_blog2_tree_spec_decoding.png | ||
| tech_blog2_verify_and_accept.png | ||
| tp_ep.png | ||
| TRT_LLM_v0-5-0_H100vA100_1st.png | ||
| TRT_LLM_v0-5-0_H100vA100_tps.png | ||
| XQA_ThroughputvsLatency.png | ||