Francisco Melo
Francisco Melo
Hello, I'm using the platform orangecrab and I've built a SoC using litex. I'm taking advantage of orangecrab's external SDRAM and thus I'm not using integrated main ram ([integrated_main_ram_size](https://github.com/enjoy-digital/litex/blob/85d6cb4b8df98730bd83b412dff6108df188bbb4/litex/soc/integration/soc_core.py#L88) =...
Hello! I was wondering if Luna can be used out of the box as USB-UART bridge with an example. Do you think it's possible to generate a DTR and a...
Hello, Clearly my PC is not as juicy as yours. I'm attempting to load the model with `LlamaForCausalLM.from_pretrained()` but the script crashes since I don't have enough RAM (I only...
Hello, 1. Could you explain me the need for doing this? https://github.com/huawei-noah/Efficient-Computing/blob/5731ac7a056dfbe80d772d826e10497a1879a9e2/BinaryNetworks/AdaBin/cifar10/utils/binarylib.py#L67 2. In inference (with no training), the `gradient_approx()` works simply as a `sign()`, correct? Thanks in advance
Hello, **Bug details:** ``` File "onnx2torch/onnx2torch/node_converters/reduce.py", line 159, in forward return torch.sum(input_tensor, dim=self._axes, keepdim=self._keepdims) TypeError: sum() received an invalid combination of arguments - got (Tensor, keepdim=int, dim=list), but expected one...
Hey! When I try to flash my "image" (image contains a bitstream+ some memory contents I need stored in my flash memory) into the external flash memory of a ECP5...
Hello, I'm trying to flash the r2.0 bootloader foboot-v3.0-orangecrab-r0.2-25F.bit into my orangecrab with ecpprog (latest commit). However, the verification always fails at byte `4096`, I tried many times and the...
Let's explore using https://github.com/fern-api/fern for automatic api docs
Right now, if a session reaches the max token context size, it seg faults. This cannot happen