-
My use case is inference acceleration on a CPU using TensorFlow Serving, and my hardware architecture is AArch64 (ARMv8). Currently, I've noticed that with oneDNN enabled, the performance bottleneck i…
-
Context: #4, #20. Global state is problematic, but even if we make it explicit, the ability to have [arbitrary length switches](https://github.com/penzn/flexible-vectors/blob/416dbcb3c1ccd67b6dd522656…
-
I'm struggling with the steps to compile a custom kernel.
```
cd build/linux
make menuconfig
# next .. load arch/arm64/configs/longanpi_3h_defconfig
cd ../..
sh mklinux.sh
```
using the menu…
-
Thanks for reaching out! I like the direction, IMO it's important to have unknown-length types for two reasons:
1) to allow using all of SSE4/AVX2/AVX-512 without source code changes;
2) to enable u…
penzn updated
3 years ago
-
```csharp
// Generated by Fuzzlyn v2.3 on 2024-08-23 10:51:00
// Run on Arm64 Windows
// Seed: 11139641262794602128-vectort,vector64,vector128,armsve
// Reduced from 38.6 KiB to 0.6 KiB in 00:00:3…
-
I built whisper.cpp from source on a Galaxy S23 ultra (Android 13) in Termux, and when I run the following command...
`whisper.cpp/main -f whisper.cpp/samples/jfk.wav -m whisper.cpp/models/ggml-bas…
-
### What is the issue?
No issues with any model that fits into a single 3090 but seems to run out of memory when trying to distribute to the second 3090.
```
INFO [wmain] starting c++ runner | ti…
-
- Using latest EA build (24EA16) on M1 Mac (ARM) for a JEP338 benchmark in Scala, s. article:
https://alexklibisz.com/2023/02/25/accelerating-vector-operations-jvm-jdk-incubator-vector-project-panama…
-
```
$ qemu-aarch64 -g 1234 /tmp/test.o
$ ./bin/lldb /tmp/test.o -o "log enable gdb-remote packets" -o "gdb-remote 1234"
(lldb) register read --all
general:
x0 = 0x0000000000000000
…
-
### Before submitting your bug report
- [X] I believe this is a bug. I'll try to join the [Continue Discord](https://discord.gg/NWtdYexhMs) for questions
- [X] I'm not able to find an [open issue](ht…