# Unable to Process Concurrent User Request

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Funable-to-process-concurrent-user-request%2F2385%3E%5C
**Category:** Models\
**Created:** [December 1, 2020, 6:43am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Funable-to-process-concurrent-user-request%2F2385 "2020-12-01T06:43:19Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![ankitsingi007](https://avatars.discourse-cdn.com/v4/letter/a/5f9b8f/32.png) [@ankitsingi007](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fankitsingi007)%5C
**Post date:** [December 1, 2020, 6:43am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Funable-to-process-concurrent-user-request%2F2385%2F1 "2020-12-01T06:43:20Z")

</div>

I am using the [https://huggingface.co/ktrapeznikov/biobert\_v1.1\_pubmed\_squad\_v2/tree/main#](https://huggingface.co/ktrapeznikov/biobert_v1.1_pubmed_squad_v2/tree/main#)  
for the question answering model. I am sending around 50 abstracts from Pubmed and then asking the question. It is working fine for 1 user , but when scale to 10 concurrent users the model is taking too long. Can anybody help

---

<div class="post-metadata">

**Author:** ![FL33TW00D](https://avatars.discourse-cdn.com/v4/letter/f/e0b2c6/32.png) [@FL33TW00D](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FFL33TW00D)%5C
**Post date:** [December 1, 2020, 9:19am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Funable-to-process-concurrent-user-request%2F2385%2F2 "2020-12-01T09:19:50Z")

</div>

There’s a number of avenues that you could use to reduce inference time:

1. Scale your deployment vertically or horizontally.
2. Move to a smaller model.
3. Improve your preprocessing/postprocessing efficiency.