-
llama.cpp runs incredibly fast on Apple silicon, I ran a build with pure CPU, and it is closer to the memory bandwidth e.g. 28 tokens/s on an M3 Pro.
llama3.java seems to be rather slow on Apple sili…
mukel updated
1 month ago
-
**Describe the project you are working on:**
I am not working on a specific project, however I am very interested in the performance of the GDScript compiler and execution engine.
**Describe t…
-
> It's worth noting that native_compute performs significantly worse than OCaml HOAS, though the two should be similar; probably native_compute does not use flambda optimization options at all.
Ind…
-
most of our use of pow is inefficient if not improper:
https://github.com/search?q=repo%3Acms-sw%2Fcmssw+pow%28+language%3AC%2B%2B&type=code&l=C%2B%2B&p=5
1) pow(x,2) : no the compiler will not subs…
-
```
What steps will reproduce the problem?
1.Added micro-profiler in MSVS 2010 professional edition. Till this it is
profiling as expected.
2.Than toggle compiler to Intel Parallel Studio C++ profes…
-
```
What steps will reproduce the problem?
1.Added micro-profiler in MSVS 2010 professional edition. Till this it is
profiling as expected.
2.Than toggle compiler to Intel Parallel Studio C++ profes…
-
DrMemory-Windows-1.10.1-3
UnityYAMLMerge.exe 64 bit app
Running through drmemory
Runs fine using plain commandline
I've run drmemory with -coverage and the put it through drcov2lcov and finally used …
-
| | |
| --- | --- |
| Bugzilla Link | [20543](https://llvm.org/bz20543) |
| Version | trunk |
| OS | All |
| CC | @pogo59,@rnk,@silvasean |
## Extended Description
I have tried to find documentati…
-
### 🚀 The feature, motivation and pitch
# Motivation
Current torch inductor only support non-Windows OS. This RFC is proposal to add a new CPP builder which also support Windows OS.
Firstly, we can l…
-
### Description
I'm trying to compile a code where I have the following logic
```fortran
#ifdef USE_MPI
USE MPI
#else
#ifdef USE_MPIF90_STUBS
USE mpif90_stubs
#endif
#endif
```
…
rweed updated
5 months ago