Why we write our own C and C++ inference engines

(localai.io)

12 points | by eatonphil 3 days ago ago

6 comments

  • scottcodie a few seconds ago

    I did took a native c++ approach when writing a relational transformers engine (RelativeDB). My journey was pytorch -> c++ -> Triton (lang). While C++ was more performant than Triton, I couldn't afford to optimize on every gpu. I just accepted the ~15% throughput loss for my cloud service, which honestly wasn't bad for the amount of flexibility I got out of it.

    But the cpp port of vllm looks great, that'd be great if you'll maintain that. I hit the same limitations with vllm.

  • dennis16384 an hour ago

    I had a similar success with Model2Vec static embedder and NER inference (both GGUF, compiled for WASM), ported to plain C from ONNX Runtime.

    Wasm size from 30Mb to 300kb and 1.5x speedup. It's definitely worth it for performance or distribution size.

  • stephbook an hour ago

    Should have started with writing your own blog posts.

    • nnevatie an hour ago

      Came here to say the same. Really tiring to read these slop-infested posts, where everything has the “right shape”.

    • altmanaltman 33 minutes ago

      I went through the post because of your comment but it really doesn't look like AI slop. Can you please share why you feel like its slop and not written by a human? I can also say "should have started writing your own comments" to you and its unfalsifiable. Blanket accusations with no proof is not a good move really.

  • adithyassekhar 34 minutes ago

    What you get: X is the A, Y is the B.