client VS llama.cpp

- While keeping power utilization below X

They will take the exported model and dynamically deploy the package to a triton instance running on your actual inference serving hardware, then generate requests to meet your SLAs to come up with the optimal model configuration. You even get exported metrics and pretty reports for every configuration used/attempted. You can take the same exported package, change the SLA params, and it will automatically re-generate the configuration for you.

- Performance on a completely different level. TensorRT-LLM especially is extremely new and very early but already at high scale you can start to see > 10k RPS on a single node.

- gRPC support. Especially when using pre/post processing, ensemble, etc you can configure clients programmatically to use the individual models or the ensemble chain (as one example). This opens up a very wide range of powerful architecture options that simply aren't available anywhere else. gRPC could probably be thought of as AsyncLLMEngine, it can abstract actual input/output or expose raw in/out so models, tokenizers, decoders, etc can send/receive raw data/numpy/tensors.

- DALI support[5]. Combined with everything above, you can add DALI in the processing chain to do things like take input image/audio/etc, copy to GPU once, GPU accelerate scaling/conversion/resampling/whatever, and get output.

vLLM and HF TGI are very cool and I use them in certain cases. The fact you can give them a HF model and they just fire up with a single command and offer good performance is very impressive but there are an untold number of reasons these providers use Triton. It's in a class of its own.

[0] - https://mistral.ai/news/la-plateforme/

[1] - https://www.cloudflare.com/press-releases/2023/cloudflare-po...

[2] - https://www.nvidia.com/en-us/case-studies/amazon-accelerates...

[3] - https://github.com/triton-inference-server/model_navigator

[4] - https://github.com/triton-inference-server/client/blob/main/...

[5] - https://github.com/triton-inference-server/dali_backend

Inference servers essentially turn a model running on CPU and/or GPU hardware into a microservice.

Many of them support the kserve API standard[0] that supports everything from model loading/unloading to (of course) inference requests across models, versions, frameworks, etc.

So in the case of Triton[1] you can have any number of different TensorFlow/torch/tensorrt/onnx/etc models, versions, and variants. You can have one or more Triton instances running on hardware with access to local GPUs (for this example). Then you can put standard REST and or grpc load balancers (or whatever you want) in front of them, hit them via another API, whatever.

Now all your applications need to do to perform inference is do an HTTP POST (or use a client[2]) for model input, Triton runs it on a GPU (or CPU if you want), and you get back whatever the model output is.

Not a sales pitch for Triton but it (like some others) can also do things like dynamic batching with QoS parameters, automated model profiling and performance optimization[3], really granular control over resources, response caching, python middleware for application/biz logic, accelerated media processing with Nvidia DALI, all kinds of stuff.

[0] - https://github.com/kserve/kserve

[1] - https://github.com/triton-inference-server/server

[2] - https://github.com/triton-inference-server/client

[3] - https://github.com/triton-inference-server/model_analyzer

if you can compile stuff, then looking at llama.cpp (what ollama uses) is also interesting: https://github.com/ggerganov/llama.cpp

the server is here: https://github.com/ggerganov/llama.cpp/tree/master/examples/...

And you can search for any GGUF on huggingface

Yes, Metal seems to allow a maximum of 1/2 of the RAM for one process, and 3/4 of the RAM allocated to the GPU overall. There’s a kernel hack to fix it, but that comes with the usual system integrity caveats. https://github.com/ggerganov/llama.cpp/discussions/2182

For anyone interested in exploring this, llama.cpp has an example implementation here:

https://github.com/ggerganov/llama.cpp/tree/master/examples/...

Getting started with LLMs can be intimidating. In this tutorial we will show you how to fine-tune a large language model using LoRA, facilitated by tools like llama.cpp and KitOps.

well https://github.com/ggerganov/llama.cpp/issues/6849