kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

[None][doc] Fix blog4 typo (#6612)

Browse Source 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
This commit is contained in:
Enwei Zhu 2025-08-05 10:20:37 +08:00 committed by GitHub
parent 6a3a921284
commit 899b74c357
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/blogs/tech_blog/blog4_Scaling_Expert_Parallelism_in_TensorRT-LLM.md
View File

@ -503,7 +503,7 @@ Let's use some representative workloads to illustrate the performance impact wit
</div>
<p align="center"><sub><em>Figure 24: EP impact over MoE Group GEMM and EP communication</em></sub></p>
In Figure 24, it can be observed that by increasing the EP size from 4 to 72, the MoE Group GEMM computation time gets reduced, while the EP communication time (for EP4/EP8 Reduce/Scatter is used, while for EP>8 All2All is used) stays almost constant.
When the EP size increases from 18 to 32, the speed-up diminishes. We are working on optimizing it.
When the EP size increases from 18 to 72, the speed-up diminishes. We are working on optimizing it.
Next, let's use some representative workloads to understand the performance impact with EPLB.
<div align="center">