Henry Tu
Henry Tu
Reverts https://github.com/llvm/torch-mlir/pull/1183 after addressing nightly build failure
Currently LTC fails to build using the OOT CI config due to this linkage error: https://github.com/llvm/torch-mlir/runs/7549301528?check_suite_focus=true Currently we work around this by setting `TORCH_MLIR_ENABLE_LTC=OFF` in cmake, which excludes LTC from...
Hi @silvasean, we're now able to trace a Huggingface BERT model with full forward and backwards graph, but we had to add support for a few ops to torch-mlir. Looking...
Hey @silvasean, we're going to start writing tests for the LTC components of Torch MLIR soon. Here's what we were thinking: - e2e test for the example LTC backend implementation,...
Re: https://github.com/llvm/torch-mlir/pull/1283#issuecomment-1227744684 https://github.com/llvm/torch-mlir/pull/1283 resolves an issue with the release build of Torch-MLIR where the shared libraries for LTC were not being properly discovered. This was not detected earlier, since CI...
After https://github.com/llvm/torch-mlir/pull/1205, we discovered that LTC has trouble linking on macOS-arm64. Detailed logs here: https://github.com/llvm/torch-mlir/runs/7907158318?check_suite_focus=true As such, we have disabled LTC build on macOS temporarily. ``` Undefined symbols for architecture...
Adding Cerebras Inference as an API provider. It looks like the other providers use the [legacy OpenAI API ](https://platform.openai.com/docs/guides/completions) but we prefer the [new chat completion API](https://platform.openai.com/docs/guides/text-generation). As a result...