intel / intel/xFasterTransformer

1st token latency has poor performance than other framework

Open
#509 12 comments 0 reactions 0 assignees View on GitHub
Dominant language
C++
Stars
435
Forks
76
PR merge metrics
No merged PRs in 30d

Description

when i test the model "DeepSeek-R1-Distill-Qwen-7B", the TTFT metrix worse than openvino,I don't know if it's normal. If so, is there any way to improve this performance

![Image](https://github.com/user-attachments/assets/68eb8241-5439-48bf-9659-2d4189f0fe5b)

Environment:
CPU:2x8592+
Memory: 16x Hynix HMCG94AGBRA179N 64G DDR5 2Rx4

Benchmark command:

![Image](https://github.com/user-attachments/assets/e77970a7-9a9a-4ac3-befa-6b7f796e8221)

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.