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> |
||
|---|---|---|
| .. | ||
| .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 | ||
| tp_ep.png | ||
| TRT_LLM_v0-5-0_H100vA100_1st.png | ||
| TRT_LLM_v0-5-0_H100vA100_tps.png | ||
| XQA_ThroughputvsLatency.png | ||