-
### 🚀 The feature, motivation and pitch
The current builtin Host CPU memory allocator is a little problematic to support memory allocated by special interfaces like remote memory, apu memory, ..
H…
-
Hi, thanks for LodePNG.
To make the custom allocator functionality (LODEPNG_NO_COMPILE_ALLOCATORS) useful to me, I need the lodepng_malloc/realloc/free functions to accept an extra void *user_arg arg…
-
Hi,
It would be very useful to support custom allocators. For example in GPGPU applications buffers preferred to be allocated by the driver ([cudaMallocHost](http://horacio9573.no-ip.org/cuda/group…
-
**Is your feature request related to a problem? Please describe.**
We utilize gpu_cache in the Deep Graph Library project. We would like the gpu_cache to be able to use a custom allocator. That way, …
-
nDPI has always been able to use custom memory allocators, via `set_ndpi_malloc()` and `set_ndpi_free()` functions.
But looking at the code, I started to have a doubt: are these functions supposed to…
-
Capturing an offline discussion with @wsmoses
Stage 1:
- allow frontend to register a custom allocation function for tapes
- Needs some thought on CUDA device
- Address space might differ f…
-
As described in https://github.com/oneapi-src/unified-runtime/issues/803, the use of `RTLD_DEEPBIND` in dylib.rs [1] can cause rust-analyzer-proc-macro-srv to crash when a custom memory allocator is p…
-
### 🚀 The feature, motivation and pitch
I'm training models on cuda and I'm struggling with cuda OOM error. When I customized `torch.cuda.CUDAPluggableAllocator` with `cudaMallocManaged`, I solved th…
-
Anything using a custom allocator cannot be fuzzed, even if the same allocator is chosen in the fuzzer script.
shahn updated
7 years ago
-
[Customized allocator for standard collections](https://github.com/rust-lang/rfcs/pull/1398) This will be a rather exciting feature for us if it can land.
### Use case
A std lib's data structure …