-
Blackole feature, we want to support harvesting DRAM cores same way we support Tensix harvesting
-
Hi Yifan,
I would like to change the DRAM and cache sizes of GPUs to run light workloads in a multi-GPU setting. I understand that these sizes, along with the internal properties of DRAM and caches…
-
Hi, I have a problem with the u-boot shipped with Ubuntu and Debian images. I have a stock of Orange Pi Zero 3 with 2GB of RAM and this is happening on the batch 24-01 (I don't know if it is important…
-
I tried the FEL method on two robots, but after rebooting I can't get access via SSH.
Log via uart:
`fes commit : fc3061df4dbd4153819b2d2f141d82b88fea51cf
beign to init dram
DRAM DRIVE INFO: V…
-
Hi,
I have run DRAM-v on Virsorter2 processed sequences and got amg_summary.tsv. In that output file, AMGs are listed, so to say, in two groups: some have TRUE in the potential_amg column (=gene_id_o…
-
We get some loose nodes:
For mlir:
```mlir
#device = #tt.device, l1Map = (d0, d1)[s0, s1] -> (0, d0 floordiv …
-
**Is your feature request related to a problem? Please describe.**
Hello,
The recent issue I'm facing is with **embedding forward**, an operation where values need to be copied from the weight tenso…
-
**Describe the bug**
1d and 2d matmuls support padding in their outputs e.g. N does not need to exactly divide into tiles and cores. dram-sharded matmuls have some of the code for padding support but …
-
## Summary
`forge/test/mlir/test_ops_tf.py::test_dual_conv2d` fails on Blackhole: Tensor mismatch.
## Observations
1. The output values are totally different.
2. Forge compilation looks fine. The s…
-
pytest tests/tt_eager/python_api_testing/unit_testing/misc/test_layernorm_sharded.py
```
=============================================================== short test summary info ======================…