EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[Doc]modify pcp tutorial doc (#5440)

Browse Source 
### What this PR does / why we need it?
modify pcp tutorial doc

Because some optimization points have been submitted as PRs and haven't
been merged yet, I'll update the performance data now and refresh it
again after the PRs are merged.

- vLLM version: release/v0.13.0
- vLLM main:
81786c8774

Signed-off-by: weiguihua2 <weiguihua2@huawei.com>
This commit is contained in:
weiguihua2
2025-12-27 17:47:09 +08:00
committed by GitHub
parent 77cd960524
commit c30c3dc831
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/tutorials/long_sequence_context_parallel_multi_node.md
View File

@@ -369,4 +369,4 @@ After about several minutes, you can get the performance evaluation result.
| dataset | version | metric | mode | ttft |
|---------| ----- |-------------|------|--------|
| random | - | performance | perf | 15.6s |
| random | - | performance | perf | 20.7s |