# FP16 Inference with YOLOX Doesn't Provide Speedup

**URL:** <https://discuss.tvm.apache.org/t/fp16-inference-with-yolox-doesnt-provide-speedup/14422>\
**Category:** Troubleshooting\
**Created:** [February 23, 2023, 10:13pm UTC](https://discuss.tvm.apache.org/t/fp16-inference-with-yolox-doesnt-provide-speedup/14422 "2023-02-23T22:13:12Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![alopez\_13](https://discuss.tvm.apache.org/user_avatar/discuss.tvm.apache.org/alopez_13/32/786_2.png) [@alopez\_13](https://discuss.tvm.apache.org/u/alopez_13)\
**Post date:** [February 24, 2023, 4:04pm UTC](https://discuss.tvm.apache.org/t/fp16-inference-with-yolox-doesnt-provide-speedup/14422/2 "2023-02-24T16:04:49Z")

</div>

Hello,

This [thread](https://discuss.tvm.apache.org/t/expected-performance-for-tomixedprecision-float16/14428) may be useful. TLDR unless you use Tensor Core FP16 will not give you the performance improvements seen in TRT.

---

_[View the full topic](https://discuss.tvm.apache.org/t/fp16-inference-with-yolox-doesnt-provide-speedup/14422)._