Running a 28.9M parameter LLM on an $8 microcontroller
51–60 of 79 posts
Re: Running a 28.9M parameter LLM on an $8 microcontroller
#52Wont this wear out the flash memory quickly? I wonder hiw many read cycles can it survive
It's write and/or erase cycles that cause wear.
Re: Running a 28.9M parameter LLM on an $8 microcontroller
#53Earlier quoted context omitted.
There's a neat project out there that can read your water meter into home assistant using an ESP32+camera+computer vision. I imagine a small TPU like this could be very useful for similar projects. More compute means higher resolutions and more reliability.
Interested in this. Link please
Re: Running a 28.9M parameter LLM on an $8 microcontroller
#54Re: Running a 28.9M parameter LLM on an $8 microcontroller
#55Re: Running a 28.9M parameter LLM on an $8 microcontroller
#56Wont this wear out the flash memory quickly? I wonder hiw many read cycles can it survive
Flash wears out from writing and the answer is in the tens to hundreds of thousands of writes per cell.
Re: Running a 28.9M parameter LLM on an $8 microcontroller
#57Earlier quoted context omitted.
Don't forget the 128 bit vector ISA with 32 registers, supporting up to 64 bit int and FP, and with LMUL=8 you can process 1024 bits with a single instruction (at 3 cycles per 128 bits for most operations). Fully supported by GCC and CLANG (xTHeadVector) and compatible with RVV 1.0 with just a command line switch if you use the C intrinsic functions. (a lot of code working on 8 bit elements is binary compatible with…
Meaning, minus possible required bug fixes, all the frontend languages supported on a full instal of either GCC or LLVM.
Re: Running a 28.9M parameter LLM on an $8 microcontroller
#58It's crazy what $5 can buy you in a microcontroller these days. Have a look at these Milk-V boards: https://milkv.io The duo has up to 256MB of memory, and a 1TOPS@INT8 TPU. They run Linux and are $5. I bought 5!
It really puts into perspective how much of a leech ARM has been on the entire industry. What being a monopoly does to a mfer.
The arm experiment ran its course though; the power one vendor had in the marketplace started to be abused for the benefit of the IP holder and detriment to others. Now RISC-V is going one step further with a completely open ISA and also completely open designs. This is an excellent development in the nick of time.
I wonder how Apple feels about arm64 and RISC-V now. They could have probably bought ARM at any point but maybe never considered it to avoid anti-monopoly blowback.
Re: Running a 28.9M parameter LLM on an $8 microcontroller
#59Re: Running a 28.9M parameter LLM on an $8 microcontroller
#60Earlier quoted context omitted.
Meaning, minus possible required bug fixes, all the frontend languages supported on a full instal of either GCC or LLVM.
The wild thing is that this SoC is a heterogenous compute device. It has three different kinds of cores: a pretty beefy arm64 core and two different RISC-V cores: a 1Ghz one for running Linux and a 700Mhz one dedicated to running a real-time operating system. The arm64 core can also run its own OS.