Steven S. Lyubomirsky

Results 25 issues of Steven S. Lyubomirsky

I encountered this when trying to run [this script](https://github.com/tlc-pack/relax/blob/relax/apps/relax_examples/e2e_auto_tir.py) over RPC on machines with v100's. Though it was done using Relax, @zxybazh says he thinks this can probably be triggered...

type: bug

TVM has recently switched to C++17. CUDA support with C++17 requires CMake past version 3.18, according to @vinx13. However, the current CMake version check in `CMakeLists.txt` is not checking for...

This PR fixes the issue noted in #288 in which the `BlockBuilder`'s `ExprMemo` can store entries between visits, which resulted in violating scoping rules when an expression was visited twice...

The idea of fuzzing Relax has been raised in some community meetings, so we may discuss how we might approach this problem and how a Relax fuzzer could be implemented....

[Rendered view.](https://github.com/slyubomirsky/relax/blob/spec-draft/relax_spec.md) This document is a draft language specification for Relax. The purpose of the language specification is to serve as a technical reference describing the language's behavior in sufficient...

From early on, Relax has adopted ANF* as a standard representation for passes and much of the compiler infrastructure is built around assuming that passes will be normalized into ANF....

Presently, any wildcard dimension in a shape annotation (namely, written as `_`) is parsed as a fresh shape variable. For example, let us consider the following function: ```python @tvm.script.ir_module class...

Currently, in `R.call_packed`, we give a type argument indicating the return type, but we do not indicate the argument types, which results in less informative type checking. I think there...

UX

Per the discussion in the August 16 community meeting, there are some unresolved choices we may make about type-checking behavior in Relax and what interface it should present to users....

UX

Currently, there is no way to indicate which packed funcs are safe to call inside a dataflow block, since any of them can potentially have side effects. It would be...