Our great sponsors
-
-
-
WorkOS
The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.
-
AdaptiveCpp
Implementation of SYCL and C++ standard parallelism for CPUs and GPUs from all vendors: The independent, community-driven compiler for C++-based heterogeneous programming models. Lets applications adapt themselves to all the hardware in the system - even at runtime!
-
-
-
-
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
> While I agree that it's much more effort to get things working on AMD cards than it is with Nvidia, I was a bit surprised to see this comment mention Whisper being an example of "5-10x as performant".
It easily is. See the benchmarks[0] from faster-whisper which uses Ctranslate2. That's 5x faster than OpenAI reference code on a Tesla V100. Needless to say something like a 4080 easily multiplies that.
> https://www.tomshardware.com/news/whisper-audio-transcriptio... is a good example of Nvidia having no excuses being double the price when it comes to Whisper inference, with 7900XTX being directly comparable with 4080, albeit with higher power draw. To be fair it's not using ROCm but Direct3D 11, but for performance/price arguments sake that detail is not relevant.
With all due respect to the author of the article this is "my first entry into ML" territory. They talk about a 5-10 second delay, my project can do sub 1 second times[1] even with ancient GPUs thanks to Ctranslate2. I don't have an RTX 4080 but if you look at the performance stats for the closest thing (RTX 4090) the performance numbers are positively bonkers - completely untouchable for anything ROCm based. Same goes for the other projects I linked, lmdeploy does over 100 tokens/s in a single session with LLama2 13b on my RTX 4090 and almost 600 tokens/s across eight simultaneous sessions.
> EDIT: Also using CTranslate2 as an example is not great as it's actually a good showcase why ROCm is so far behind CUDA: It's all about adapting the tech and getting the popular libraries to support it. Things usually get implemented in CUDA first and then would need additional effort to add ROCm support that projects with low amount of (possibly hobbyist) maintainers might not have available. There's even an issue in CTranslate2 where they clearly state no-one is working to get ROCm supported in the library. ( https://github.com/OpenNMT/CTranslate2/issues/1072#issuecomm... )
I don't understand what you're saying here. It (along with the other projects I linked) are fantastic examples of just how far behind the ROCm ecosystem is. ROCm isn't even on the radar for most of them as your linked issue highlights.
Things always get implemented in CUDA first (ten years in this space and I've never seen ROCm first) and ROCm users either wait months (minimum) for sub-par performance or never get it at all.
[0] - https://github.com/guillaumekln/faster-whisper#benchmark
[1] - https://heywillow.io/components/willow-inference-server/#ben...
Yep, did exactly that. IMO he threw a fit, even though AMD was working with him squashing bugs. https://github.com/RadeonOpenCompute/ROCm/issues/2198#issuec...
Not natively, but AdaptiveCpp (previously hiSycl, then OpenSycl) has a single source single compiler pass, where they basically store LLVM IR as an intermediate representation.
https://github.com/AdaptiveCpp/AdaptiveCpp/blob/develop/doc/...
Performance penalty was within ew precents, at least according to the paper (figure 9 and 10)
For LLM inference, a shoutout to MLC LLM, which runs LLM models on basically any API that's widely available: https://github.com/mlc-ai/mlc-llm
I wouldn’t say ROCm code is “slower”, per se, but in practice that’s how it presents. References:
https://github.com/InternLM/lmdeploy
https://github.com/vllm-project/vllm
https://github.com/OpenNMT/CTranslate2
You know what’s missing from all of these and many more like them? Support for ROCm. This is all before you get to the really wildly performant stuff like Triton Inference Server, FasterTransformer, TensorRT-LLM, etc.
ROCm is at the “get it to work stage” (see top comment, blog posts everywhere celebrating minor successes, etc). CUDA is at the “wring every last penny of performance out of this thing” stage.
In terms of hardware support, I think that one is obvious. The U in CUDA originally stood for unified. Look at the list of chips supported by Nvidia drivers and CUDA releases. Literally anything from at least the past 10 years that has Nvidia printed on the box will just run CUDA code.
One of my projects specifically targets Pascal up - when I thought even Pascal was a stretch. Cue my surprise when I got a report of someone casually firing it up on Maxwell when I was pretty certain there was no way it could work.
A Maxwell laptop chip. It also runs just as well on an H100.
THAT is hardware support.
I wouldn’t say ROCm code is “slower”, per se, but in practice that’s how it presents. References:
https://github.com/InternLM/lmdeploy
https://github.com/vllm-project/vllm
https://github.com/OpenNMT/CTranslate2
You know what’s missing from all of these and many more like them? Support for ROCm. This is all before you get to the really wildly performant stuff like Triton Inference Server, FasterTransformer, TensorRT-LLM, etc.
ROCm is at the “get it to work stage” (see top comment, blog posts everywhere celebrating minor successes, etc). CUDA is at the “wring every last penny of performance out of this thing” stage.
In terms of hardware support, I think that one is obvious. The U in CUDA originally stood for unified. Look at the list of chips supported by Nvidia drivers and CUDA releases. Literally anything from at least the past 10 years that has Nvidia printed on the box will just run CUDA code.
One of my projects specifically targets Pascal up - when I thought even Pascal was a stretch. Cue my surprise when I got a report of someone casually firing it up on Maxwell when I was pretty certain there was no way it could work.
A Maxwell laptop chip. It also runs just as well on an H100.
THAT is hardware support.
> While I agree that it's much more effort to get things working on AMD cards than it is with Nvidia, I was a bit surprised to see this comment mention Whisper being an example of "5-10x as performant".
It easily is. See the benchmarks[0] from faster-whisper which uses Ctranslate2. That's 5x faster than OpenAI reference code on a Tesla V100. Needless to say something like a 4080 easily multiplies that.
> https://www.tomshardware.com/news/whisper-audio-transcriptio... is a good example of Nvidia having no excuses being double the price when it comes to Whisper inference, with 7900XTX being directly comparable with 4080, albeit with higher power draw. To be fair it's not using ROCm but Direct3D 11, but for performance/price arguments sake that detail is not relevant.
With all due respect to the author of the article this is "my first entry into ML" territory. They talk about a 5-10 second delay, my project can do sub 1 second times[1] even with ancient GPUs thanks to Ctranslate2. I don't have an RTX 4080 but if you look at the performance stats for the closest thing (RTX 4090) the performance numbers are positively bonkers - completely untouchable for anything ROCm based. Same goes for the other projects I linked, lmdeploy does over 100 tokens/s in a single session with LLama2 13b on my RTX 4090 and almost 600 tokens/s across eight simultaneous sessions.
> EDIT: Also using CTranslate2 as an example is not great as it's actually a good showcase why ROCm is so far behind CUDA: It's all about adapting the tech and getting the popular libraries to support it. Things usually get implemented in CUDA first and then would need additional effort to add ROCm support that projects with low amount of (possibly hobbyist) maintainers might not have available. There's even an issue in CTranslate2 where they clearly state no-one is working to get ROCm supported in the library. ( https://github.com/OpenNMT/CTranslate2/issues/1072#issuecomm... )
I don't understand what you're saying here. It (along with the other projects I linked) are fantastic examples of just how far behind the ROCm ecosystem is. ROCm isn't even on the radar for most of them as your linked issue highlights.
Things always get implemented in CUDA first (ten years in this space and I've never seen ROCm first) and ROCm users either wait months (minimum) for sub-par performance or never get it at all.
[0] - https://github.com/guillaumekln/faster-whisper#benchmark
[1] - https://heywillow.io/components/willow-inference-server/#ben...