22 comments

  • engzaanin 3 hours ago ago

    That makes sense. The title initially sounded like a general llama.cpp speedup on Apple Silicon, but if the improvement comes from fixing kernel selection inside Virtualization.framework VMs, that distinction is pretty important.

  • simonw 3 hours ago ago

    It looks to me like this won't speed up llama.cpp for everyone, just for users running it in this particular kind of Virtualization.framework VM.

    The fix here works around a problem where the VM was causing llama.cpp to select the wrong kernels.

    • frabonacci 3 hours ago ago

      > this won't speed up llama.cpp for everyone, just for users running it in this particular kind of Virtualization.framework VM.

      correct. these figures apply to llama.cpp inside the macOS guest configuration we tested. Lume is the VM frontend we used, while Apple's Virtualization.framework provides the virtual GPU. bare-metal llama.cpp is unaffected.

      > The fix here works around a problem where the VM was causing llama.cpp to select the wrong kernels.

      mostly, with one nuance: llama.cpp is selecting the correct kernels for the capability answers it receives. the stock guest reports an older Apple GPU family and a 32 KB threadgroup memory limit, so llama.cpp chooses slower kernels. Our process-scoped layer reports the tested Apple 9 and 64 KB values while allowing llama.cpp to select newer paths that the paravirtual GPU successfully execute

      the layer itself though works at the Metal API boundary, independently of llama.cpp. other Metal compute and graphics apps now may select newer paths from the same capability answers, although this is still preliminary and each app needs separate testing. for example, MLX-LM stayed flat in our tests

      historically related limitations have been coming up across Apple Silicon VM frontends for a while e.g. Tart tracked MPS/GPU support back in 2023: - https://github.com/openai/tart/issues/501 - https://github.com/openai/tart/issues/1032

      UTM also has related cases where apps detect the Apple paravirtual Metal device but falls back to software rendering: https://github.com/utmapp/UTM/issues/7671

      • sitkack an hour ago ago

        why do use ai to write your posts ?

        • Aldo_MX an hour ago ago

          Why do you expect an AI engineer to manually write prose?

    • octocop an hour ago ago

      a win is still a win

  • aeriose 2 hours ago ago

    What I don't get, which this article doesn't talk about, why would Apple’s Virtualization.framework expose a lesser Metal profile instead of reporting all capabilities supported by the host GPU?

    • hugmynutus an hour ago ago

      Because nobody knows.

      Apple doesn't let you "pass" the GPU through to a VM like most other ARM/x86_64 processors (forwarding interrupts and PCIe memory regions). There are symbols defined to do this within the kernel (if you dump the binary) but they aren't used in retail macos.

      Instead you end up creating a paravirtual device that emulates the GPU acting like a 'normal PCI device' which you give to clients. This is usually reserved (by other hardware vendors) for when you're doing multi-tenat time sharing of higher end GPUs (like Nvidia enterprise cards can do).

      These paravirtualized GPUs then just have 'less features' and Apple (being Apple) states no reason why.

    • chorizo an hour ago ago

      All M-series chips support Metal 4. Wonder if we can fix this with a simple override somewhere.

    • bestham an hour ago ago

      Because it cannot be safely virtualised?

  • thehamkercat 3 hours ago ago

    > 11.08× faster and generated tokens 16.36× faster than the same workload in the same stock VM.

    So this was the comparison, for me the title was a bit confusing

    • frabonacci 3 hours ago ago

      yeah fair point. it's always tricky to get the whole idea across within HN's title limit. tldr: we ran the same workload in the same Lume macOS VM on the same Apple Silicon host, first with stock Metal capability reporting and then with our process-scoped dynamic library. The 11.08x figure is prompt processing, while 16.36x is token generation. the mechanism technically extends to graphics workloads too but these figures are specifically from llama.cpp

  • azinman2 3 hours ago ago

    I don’t understand what Apple 1-9 are. At first I thought it was M series chips but there is no M9 (yet)

    • niklasbuschmann 3 hours ago ago
      • wtallis 3 hours ago ago

        So those generation numbers aren't really anchored to Apple's hardware designs. It's just counting from when Apple introduced the Metal API, and the first several generations were when the GPU cores Apple was using were still nominally PowerVR designs.

        • frabonacci an hour ago ago

          yeah the naming is confusing. Apple family 9 isnt M9, it's a Metal GPU feature family. Apple maps family 7 to M1, family 8 to M2, family 9 to M3/M4, and family 10 to M5

  • luciana1u 2 hours ago ago

    my whole setup is buy more RAM, run it on CPU, and tell myself the GPU is just a personality trait I'm working on.

    • cyanydeez 2 hours ago ago

      I'm hoping AMD wins when the RAM bubble bursts and their integrated AMD 395+ platform can keep getting faster and higher bandwidth.

  • shay_ker 3 hours ago ago

    I recall there was another YC startup that was working on Mac-specific ML optimizations for local inference (and perhaps fine-tuning).

    I wonder if their work is related?

  • gigatexal 2 hours ago ago

    All this work to get the Mac to be a platform useful for AI is being done despite Apple's efforts. They're famously pissed at Nvidia since the Nvidia + Intel Macs due to heat and other issues. But then the OS is a bit closed off and they move slow and are more focused on milking iOS and the App Store and services for money BUT the PA-Semi purchase and Apple Silicon and everything following it has made the hardware just so amazing and useful that despite all that people build for it.

    I love the platform. I'm happy to see people building on it.

    AND! if we ever get an M7 chip with the rumored 1.5TB of available ram all this work will not have been in vain. You think the ai acceleration is nice in the M5 wait till M7 and M8.

  • woadwarrior01 3 hours ago ago

    The Claudish in the blogpost makes it really hard to ready. Also, TinyLlama 1.1B lol.