mirror of
https://github.com/kvcache-ai/ktransformers.git
synced 2026-03-14 18:37:23 +00:00
Npu revise benchmark results and prerequisites (#1716)
* Update DeepseekR1_V3_tutorial_zh_for_Ascend_NPU.md * Update DeepseekR1_V3_tutorial_zh_for_Ascend_NPU.md * Revise Ascend NPU tutorial for Docker deployment Updated the tutorial for deploying the Ascend NPU, changing sections from 'Conda部署' to '镜像部署' and providing specific commands for Docker container setup and Python environment installation. * Update DeepseekR1 tutorial for Ascend NPU * Update DeepseekR1_V3_tutorial_zh_for_Ascend_NPU.md * Update W8A8 weight link in tutorial * Update doc/zh/DeepseekR1_V3_tutorial_zh_for_Ascend_NPU.md Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * Refactor Docker command and update package manager Updated Docker run command to simplify device specifications and corrected package manager command from 'apt' to 'yum'. * Update DeepseekR1_V3_tutorial_zh_for_Ascend_NPU.md * Revise benchmark results and prerequisites Updated performance results and hardware specifications. * Update doc/zh/DeepseekR1_V3_tutorial_zh_for_Ascend_NPU.md Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> --------- Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
@@ -1,5 +1,7 @@
|
||||
# 基准测试结果
|
||||
|
||||
在 Batchsize=4、输出长度为 1024 的条件下,性能测试结果如下:
|
||||
|
||||
| Prompt length | 1K | 2K | 4K |
|
||||
| --------------------------------- | ------ | ------ | ------ |
|
||||
| KTrans Prefill token/s | 174.68 | 169.52 | 167.15 |
|
||||
@@ -8,7 +10,7 @@
|
||||
## 先决条件
|
||||
我们在以下配置下进行了Deepseek-R1最佳性能测试:
|
||||
- 服务器型号:Atlas 2UP
|
||||
- NPU:300I A2
|
||||
- NPU:Atlas 300I A2
|
||||
- CPU: HUAWEI Kunpeng 920 7270Z
|
||||
- 内存: DDR5服务器内存(1TB)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user