Static Newsabout
za_mike157 | 32 comments

ribhu97|next|

How does this compare to modal (modal.com)? Faster cold-start? Easier config? Asking because I've used modal quite a bit for everything from fine-tuning LLMs to running etl pipelines and it works well for me, and I haven't found any real competitors for them to even think of switching.

za_mike157|parent|next|

Modal is a great platform!

In terms of cold starts, we seem to be very comparable from what users have mentioned and tests we have run.

Easier config/setup is feedback we have gotten from users since we don't have and special syntax or a "Cerebrium way" of doing things which makes migration pretty easier as well as doesn't lock you in which some engineers appreciate. We just run your Python code as is with an extra .toml setup file.

Additionally, we offer AWS Inferentia/Tranium nodes which offer a great price/performance trade-offs for many open-Source LLM's - even when using TensorRT/vLLM on Nvidia GPU's and gets rid of the scarcity problem. We plan to support TPU's and others in future.

We are listed on AWS Marketplace as well as others which means you can subtract your Cerebrium cost from your commited cloud spend.

Two things we are working on that will hopefully make us a bit different is: - GPU checkpointing - Running compute in your own cluster to use credits/for privacy concerns.

Where Modal does really shine is training/data-processing use cases which we currently don't support too well. However, we do have this on our roadmap for the near future.


doctorpangloss|parent|prev|next|

Why use modal instead of SkyPilot?

mdaniel|prev|next|

Being a toml-n00b, why is this quoted? https://github.com/CerebriumAI/examples/blob/85815f8e09e9e77...

Related to that, it seems the syntax isn't documented https://docs.cerebrium.ai/cerebrium/environments/config-file...


za_mike157|parent|next|

Do you mean why the individual file names aren't quoted?

You can see an example config file at the bottom of that link you attached - agreed we should probably make it more obvious


mdaniel|root|parent|next|

heh, I don't need an example in the docs, the whole repo is filled with examples, but unless you expect some poor soul to do $(grep -r ^include . | sort | uniq) and guess from there, what I'm saying in that the examples -- including the bare bones one in your documentation -- do not SPECIFY what the glob syntax is. The good thing about standards is that there are so many to choose from, so: python's os.glob, golang's glob, I'm sure rust-lang has one, bash, ... I'm sure I could keep going

As for the quoting part, it's mysterious to me why a structured file would use a quoted string for what is obviously an interior structure. Imagine if you opened a file and saw

  fred = "{alpha: ['beta', 'charlie''s dog', 'delta']}"
wouldn't you strongly suspect that there was some interior syntax going on there?

Versus the sane encoding of:

  fred:
    alpha:
    - beta
    - charlie's dog
    - delta
in a normal markup language, no "inner/outer quoting" nonsense required

But I did preface it with my toml n00b-ness and I know that the toml folks believe they can do no wrong, so maybe that's on purpose, I dunno


tmshapland|prev|next|

We use Cerebrium for our Mixpanel for Voice AI product (https://voice.canonical.chat). Great product. So much easier to set up and more robust than other model hosting providers we've tried (especially AWS!). Really nice people on the the team, too.

za_mike157|parent|next|

Thanks Tom! Excited to to support you and the team as you grow

android521|prev|next|

i had no idea what it does and just have this vague idea that they make it easy for you to deploy, host and use models. I looked the tutorials and was amazed by what can be done and decided to try it. My suggestion is to have more tutorials and perhaps one-click deployment for some really cool models. Another thing is support typescript and you will capture a big section of the developer market that does not come from ML background. After i finish an inteview with tutorial demo , it would be great to give an estimate of cost so that i know if i can afford to cost for my software

jono_irwin|parent|next|

Thanks for the feedback! I like the sound of all of those:

- clearer messaging - more tutorials - one-click deploys - clear & upfront costing

We have plans to add other runtimes (like Typescript) in the future but Python is our focus for now.


benjamaan|prev|next|

Congrats and thank you! We’ve been a happy customer since early on. Although we don’t have much usage, our products are mostly R&D, having Cerebrium made it super easy to launch cost effectively on tight budgets and run our own models within our apps.

The support is next level - team is ready to dive into any problem, response is super fast, and has helped us solve a bunch of dev problems that a normal platform probably won’t.

Really excited to see this one grow!!


za_mike157|parent|next|

Thank you - appreciate the kind words! Happy to continue supporting you and the team.

ekojs|prev|next|

Congrats on the launch!

We're definitely looking for something like this as we're looking to transition from Azure's (expensive) GPUs. I'm curious how you stack against something like Runpod's serverless offering (which seems quite a bit cheaper). Do you offer faster cold starts? How long would a ~30GB model load takes?


za_mike157|parent|next|

Yes RunPod does have cheaper pricing than us however they don't allow you to specify your exact resources but rather charge you the full resource (see example of A100 above) so depending on your resource requirements our pricing could be competitive since we charge you only for the resources you use.

In terms of cold starts, they mentioned their cold starts are 250ms which I am not sure what workload that is on, or if we have the same measure of cold starts. We have had quite a few customers that we have told us we are quite a bit faster 2-4 seconds vs ~10 seconds although we haven't confirmed this ourselves.

For a 30GB model, we have a few ways to speed this up such as using the Tensorizer framework from Coreweave, we cache model files in our distributed caching layer but I would need to test. We see reads of up to 1GB/s. If you tell me the model you are running (if open-source) I can get results to you - you can message me on our Slack/Discord community or email me at michael@cerebrium.ai or


spmurrayzzz|root|parent|next|

> Yes RunPod does have cheaper pricing than us however they don't allow you to specify your exact resources but rather charge you the full resource (see example of A100 above) so depending on your resource requirements our pricing could be competitive since we charge you only for the resources you use.

I may be misunderstanding your explanation a bit here, but Runpod's serverless "flex" tier looks like the same model (it only charges you for non-idle resources). And at that tier they are still 2x cheaper for A100, at your price point with them you could rent an H100.


za_mike157|root|parent|next|

Ah I see they recently cut their pricing by 40% so you are correct - sorry about that. It seems we are more expensive compared to their new pricing

spmurrayzzz|root|parent|next|

FWIW Their most expensive flex price I've ever seen for 80GB A100 was $0.00130 back in January of this year, which is still cheaper albeit by a smaller magnitude, if that's helpful at all for your own competitive market analysis.

(Congrats on the launch as well, by the way).


risyachka|root|parent|prev|next|

Yeah Runpods cold start is definitely not 250ms, not even close. Maybe for some models idk but a huggingface model 8B params takes like 30 seconds to cold start in their serverless "flash" configuration.

za_mike157|root|parent|next|

Thanks for confirming! Our cold start, excluding model load is 2-4 seconds typically for HF models.

The only time it gets much longer when companies have done a lot with very specific CUDA implementations


eh9|prev|next|

Congratulations on the launch!

I just shared this on Slack and it looks like the site description has a typo: "A serverless AI infrastructure platform [...] customers experience a 40%+ cost savings as opposed to AWS of GCP"


za_mike157|parent|next|

Thank you - updated! My team makes fun of my spelling all the time!

yuppiepuppie|prev|next|

Very nice demo!

When you ran it the first time, it took a while to load up. Do subsequent runs go faster?

And what cloud provider are you all using under the hood? We work in a specific sector that excludes us from using certain cloud providers (ie. AWS) at my company.


za_mike157|parent|next|

You are correct! After the first request, an image will be on a machine and it’s cached for future use. This makes subsequent container startups much faster. We also route requests to machines where the image is already cached as well as dedupe content between images in order to make startups faster

We are running on top of AWS however can run on top of any cloud provider as well as are working on you using your own cloud. Happy to hear more about your use case and see if we can help you at all - email me at michael@cerebrium.ai.

PS: I will state that vLLM has shocking load times into VRam that we are resolving.


abraxas|prev|next|

Would this be a direct competitor of paperspace? If yes what do you feel are your strenghts vis-a-vis paperspace?

jono_irwin|parent|next|

There are definitely some parallels between Cerebrium and paperspace, but I don't think they are a direct competitor. The biggest difference being that paperspace doesn't have a serverless offering afaik.

Cerebrium abstracts some functionality - like streaming and batching endpoints. I think you would need to build that yourself on paperspace.


abraxas|root|parent|next|

Paperspace lets you bring your own containers and will scale them automatically. I don't know whether that would qualify as "serverless".

chaosinblood|prev|next|

which ui framework do you use? it's very nice

mceachen|prev|

Good luck on your launch! Your loom drops audio after 4m25s.

za_mike157|parent|

Thanks for pointing that out!