(tvm) branch unity updated: [Unity][3rdparty] Remove TVM in 3rdparty of FlashInfer (#16155)

This is an automated email from the ASF dual-hosted git repository. junrushao pushed a commit to branch unity in repository https://gitbox.apache.org/repos/asf/tvm.git The following commit(s) were added to refs/heads/unity by this push: new 756ce9917f [Unity][3rdparty] Remove TVM in 3rdpart

Re: [PR] [Unity][3rdparty] Remove TVM in 3rdparty of FlashInfer [tvm]

junrushao merged PR #16155: URL: https://github.com/apache/tvm/pull/16155 -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: commits-unsubscr...@tvm.apache

Re: [PR] [Unity] Support constant args in `nn.ExternModule` [tvm]

junrushao merged PR #16130: URL: https://github.com/apache/tvm/pull/16130 -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: commits-unsubscr...@tvm.apache

(tvm) branch unity updated: [Unity] Support constant args in `nn.ExternModule` (#16130)

This is an automated email from the ASF dual-hosted git repository. junrushao pushed a commit to branch unity in repository https://gitbox.apache.org/repos/asf/tvm.git The following commit(s) were added to refs/heads/unity by this push: new aae1112a65 [Unity] Support constant args in `nn.Ex

Re: [PR] [OpenCL][Texture] Improved texture memory planning [tvm]

srkreddy1238 commented on PR #15058: URL: https://github.com/apache/tvm/pull/15058#issuecomment-1822138123 @tqchen can you take a look on this PR ? -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go t

(tvm) branch nightly updated (3190f284a3 -> bce82432f9)

This is an automated email from the ASF dual-hosted git repository. github-bot pushed a change to branch nightly in repository https://gitbox.apache.org/repos/asf/tvm.git from 3190f284a3 [DOC] Add v0.14.0 docs to site (#16152) add bce82432f9 [Relay][Pytorch] Add support for `aten::unfla

Re: [PR] [Relay] conv3d depthwise bug fix [tvm]

masahi commented on PR #16151: URL: https://github.com/apache/tvm/pull/16151#issuecomment-1822103573 Can you add your PT test as a test case? -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the s

(tvm) branch main updated: [Relay][Pytorch] Add support for `aten::unflatten` (#16131)

This is an automated email from the ASF dual-hosted git repository. masahi pushed a commit to branch main in repository https://gitbox.apache.org/repos/asf/tvm.git The following commit(s) were added to refs/heads/main by this push: new bce82432f9 [Relay][Pytorch] Add support for `aten::unfl

Re: [PR] [Relay][Pytorch] Add support for `aten::unflatten` [tvm]

masahi merged PR #16131: URL: https://github.com/apache/tvm/pull/16131 -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: commits-unsubscr...@tvm.apache.or

Re: [I] [FRONTEND][PYTORCH] aten:unflatten not supported [tvm]

masahi closed issue #15663: [FRONTEND][PYTORCH] aten:unflatten not supported URL: https://github.com/apache/tvm/issues/15663 -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To

Re: [PR] [Relay] conv3d depthwise bug fix [tvm]

jonghewk commented on PR #16151: URL: https://github.com/apache/tvm/pull/16151#issuecomment-1821994482 @masahi Any chance of reviewing this? -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the sp

Re: [PR] Add yolov3-tiny to the tutorial. [tvm]

preston-Glenn commented on PR #3674: URL: https://github.com/apache/tvm/pull/3674#issuecomment-1821985749 Oh that would be fantastic. Do you have any idea though why I would be experiencing worse results than the results y'all achieved on yolov3-tiny? -- This is an automated message from

Re: [PR] Add yolov3-tiny to the tutorial. [tvm]

cbalint13 commented on PR #3674: URL: https://github.com/apache/tvm/pull/3674#issuecomment-1821916285 @preston-Glenn , @siju-samuel Maybe it is time for yolov8, I will update the tutorial against stock .onnx (from ultralytics). I obtained excellent results on TVM with the yolov{5,

Re: [PR] Add yolov3-tiny to the tutorial. [tvm]

preston-Glenn commented on PR #3674: URL: https://github.com/apache/tvm/pull/3674#issuecomment-1821869890 @cbalint13 I was curious how did you evaluate this with yolov3-tiny? I've followed the tutorial that this was intended for and get results that are significantly less. I use the same we

Re: [PR] [Unity][Transform] Replace eligible operators with in-place versions in dataflow blocks [tvm]

slyubomirsky commented on code in PR #16129: URL: https://github.com/apache/tvm/pull/16129#discussion_r1401332758 ## tests/python/relax/test_dataflow_inplace.py: ## @@ -0,0 +1,462 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agr

Re: [PR] [Unity][3rdparty] Remove TVM in 3rdparty of FlashInfer [tvm]

MasterJH5574 commented on PR #16155: URL: https://github.com/apache/tvm/pull/16155#issuecomment-1821799158 cc @yzh119 @tqchen -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment

[PR] [Unity][3rdparty] Remove TVM in 3rdparty of FlashInfer [tvm]

MasterJH5574 opened a new pull request, #16155: URL: https://github.com/apache/tvm/pull/16155 This PR updates the FlashInfer version in 3rdparty, which has removed TVM from its 3rdparty to avoid recursive TVM dependency. -- This is an automated message from the Apache Git Service. To resp

(tvm) branch unity updated: [Unity][BYOC] Add cutlass finegrained decode matmul (#16144)

This is an automated email from the ASF dual-hosted git repository. wuwei pushed a commit to branch unity in repository https://gitbox.apache.org/repos/asf/tvm.git The following commit(s) were added to refs/heads/unity by this push: new 925cb2bbaa [Unity][BYOC] Add cutlass finegrained decod

Re: [PR] [Unity][BYOC] Add cutlass finegrained decode matmul [tvm]

vinx13 merged PR #16144: URL: https://github.com/apache/tvm/pull/16144 -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: commits-unsubscr...@tvm.apache.or

Re: [PR] [TOPI][Relay] Add conv2d NHWC hybrid schedule for `arm_cpu` [tvm]

ekalda commented on code in PR #16106: URL: https://github.com/apache/tvm/pull/16106#discussion_r1400924786 ## python/tvm/relay/op/strategy/arm_cpu.py: ## @@ -250,6 +257,7 @@ def conv2d_strategy_arm_cpu(attrs, inputs, out_type, target): wrap_compute_co

Re: [PR] [TOPI][Relay] Add conv2d NHWC hybrid schedule for `arm_cpu` [tvm]

ekalda commented on code in PR #16106: URL: https://github.com/apache/tvm/pull/16106#discussion_r1400918955 ## python/tvm/relay/op/strategy/arm_cpu.py: ## @@ -232,7 +232,7 @@ def conv2d_strategy_arm_cpu(attrs, inputs, out_type, target): wrap_topi_s

Re: [PR] [TOPI][Relay] Add conv2d NHWC hybrid schedule for `arm_cpu` [tvm]

Anndrey24 commented on code in PR #16106: URL: https://github.com/apache/tvm/pull/16106#discussion_r1400913110 ## python/tvm/relay/op/strategy/arm_cpu.py: ## @@ -250,6 +257,7 @@ def conv2d_strategy_arm_cpu(attrs, inputs, out_type, target): wrap_compute

Re: [PR] [TOPI][Relay] Add conv2d NHWC hybrid schedule for `arm_cpu` [tvm]

lhutton1 commented on code in PR #16106: URL: https://github.com/apache/tvm/pull/16106#discussion_r1400910045 ## python/tvm/relay/op/strategy/arm_cpu.py: ## @@ -232,7 +232,7 @@ def conv2d_strategy_arm_cpu(attrs, inputs, out_type, target): wrap_topi

Re: [PR] [TOPI][Relay] Add conv2d NHWC hybrid schedule for `arm_cpu` [tvm]

Anndrey24 commented on code in PR #16106: URL: https://github.com/apache/tvm/pull/16106#discussion_r1400897859 ## python/tvm/relay/op/strategy/arm_cpu.py: ## @@ -232,7 +232,7 @@ def conv2d_strategy_arm_cpu(attrs, inputs, out_type, target): wrap_top

Re: [I] [CI] File rename mapping when refactor unittest folder (#16110) [tvm]

zxybazh commented on issue #16138: URL: https://github.com/apache/tvm/issues/16138#issuecomment-1821276259 Thanks @Hzfengsy, the current organization of the unittests looks great! -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHu

Re: [PR] [TOPI][Relay] Add conv2d NHWC hybrid schedule for `arm_cpu` [tvm]

lhutton1 commented on code in PR #16106: URL: https://github.com/apache/tvm/pull/16106#discussion_r1400765330 ## python/tvm/relay/op/strategy/arm_cpu.py: ## @@ -232,7 +232,7 @@ def conv2d_strategy_arm_cpu(attrs, inputs, out_type, target): wrap_topi

Re: [I] [CI] File rename mapping when refactor unittest folder (#16110) [tvm]

tqchen commented on issue #16138: URL: https://github.com/apache/tvm/issues/16138#issuecomment-1821092359 cc @apache/tvm-committers -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific c

Re: [PR] [TOPI][Relay] Add conv2d NHWC hybrid schedule for `arm_cpu` [tvm]

ekalda commented on code in PR #16106: URL: https://github.com/apache/tvm/pull/16106#discussion_r1400707029 ## python/tvm/relay/op/strategy/arm_cpu.py: ## @@ -232,7 +232,7 @@ def conv2d_strategy_arm_cpu(attrs, inputs, out_type, target): wrap_topi_s

(tvm) branch unity updated: [Unity] Migrate Relax Executable/VM to `TVM_MODULE_VTABLE` Convention (#16149)

This is an automated email from the ASF dual-hosted git repository. tqchen pushed a commit to branch unity in repository https://gitbox.apache.org/repos/asf/tvm.git The following commit(s) were added to refs/heads/unity by this push: new 9a985714f3 [Unity] Migrate Relax Executable/VM to `TV

Re: [PR] [Unity] Migrate Relax Executable/VM to `TVM_MODULE_VTABLE` Convention [tvm]

tqchen merged PR #16149: URL: https://github.com/apache/tvm/pull/16149 -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: commits-unsubscr...@tvm.apache.or

[I] [rocm Bug] MIOpen Error: /long_pathname_so_that_rpms_can_package_the_debug_info/src/extlibs/MLOpen/src/ocl/convolutionocl.cpp:456: No invoker was registered for convolution forward. Was find execu

WsqRichards opened a new issue, #16154: URL: https://github.com/apache/tvm/issues/16154 ### Expected behavior set target = tvm.target.Target("rocm -libs=miopen,rocblas") After relay.build, call export_library() and run load_module again, expecting success ### Actual behavior