-
Command to run:
`pytest tests/tt_eager/python_api_testing/unit_testing/misc/test_softmax.py` (there are other tests, output shown below)
or
`pytest tests/tt_eager/python_api_testing/unit_testing/misc…
-
@marty1885 has requested query-able APIs for the following:
`MeshDevice:: get_memory_allocation_statistics`,
`MeshDevice:: get_num_dram_channels`
> To be specific, I need get_memory_allocation_stati…
-
By running this simple test in python:
```
import pytest
import torch
import ttnn
@pytest.mark.parametrize("dims", [(32, 32), (64, 64)])
def test_add_with_block_sharding(device, dims):
torch.manu…
-
As of commit [f6b220e6550521bd2663062d1ad42ecd3a41bfe7](https://github.com/NVIDIA/edk2-nvidia/commit/f6b220e6550521bd2663062d1ad42ecd3a41bfe7#diff-fc91943c930fc96e8547e6de52e8a5752ca5fb65132ffdcaf2c2…
-
I am trying to control CPU usage for the DRAM.py distill pipeline on DRAM v.1.5.0 that I am using on DRAM.py annotate .tsv output from metagenome assembled genomes. As I am using a shared lab server w…
-
`stablehlo.reshape` conversion is failing if we reshape multiple dimensions simultaneously.
An example stablehlo graph
```
module {
func.func @main(%arg0: tensor) -> tensor {
%0 = stablehlo.re…
-
Right now, loading up Llama 3B uses more then 32 GB in DRAM (closer to 64 GB).
Related issue:
- https://github.com/tenstorrent/tt-forge-fe/issues/189
-
https://github.com/CMU-SAFARI/ramulator2/blob/e62c84a6f0e06566ba6e182d308434b4532068a5/src/dram/impl/HBM2.cpp#L14
Hello,
The HBM2_8Gb preset defines a density of 6
Ozen7 updated
2 weeks ago
-
###### Build platform
window10, MSYS2, VScode , IDF4.x, jerryscript
###### Build steps
I download the jerryscript opensource project from github, and build up a environment in MSYS2,
and buil…
-
```
std::uint64_t tt_SimulationDevice::get_pcie_base_addr_from_device()
virtual void set_device_l1_address_params(const tt_device_l1_address_params& l1_address_params_);
virtual void set_device_dra…