Tianqi Chen comments

Results 637 comments of


                                            Tianqi Chen

[RELAX][PASS] Annotate Custom Scope layout pass for Adreno GPU

sorry has been busy with some stuffs, should be able to do a pass around may

[RELAX][PASS] Annotate Custom Scope layout pass for Adreno GPU

Sorry for delaying get back because of the recent focus on FFI refactoring, I think the main remaining item is the following change > StructInfo infered_sinfo = infer_struct_info_map[op](GetRef(call), builder_); >...

[Bug] android opencl kernel matmul Too large unroll parameter causes out of memory

Feel free to send a PR!

[Bug] android opencl kernel matmul Too large unroll parameter causes out of memory

gentle ping @shifeiwen

[TVMScript] Support continue and break in tvmscript

cc @Kathryn-cat @spectrometerHBH

[TVMScript] Support continue and break in tvmscript

the issue seems to be pr title

[Model] Add support for Aya-23 8B Model by Cohere

@GunjanDhanuka please rebase and cross check if things can run

[Doc] Request for suggested build-from-source options + explanation of added functionality

Thanks for the suggestion. We have some guidelines under build source details. Most other options are not necessary and do not have impact on MLC for now

[BugFix][Codegen, CUDA] Fix faulty codegen for FP8

thanks @AntonMoberg , @MasterJH5574 would be great if we can validate this PR

[CUDA][onnx-frontend]add deformconv2d converter

We are moving toward relax as the new graph IR and relay is mostly in legacy maintaining mode, would be good to see if we can add relax support