[tvm] branch last-successful updated (5ed94eefad -> 71f32ca4e8)

This is an automated email from the ASF dual-hosted git repository. github-bot pushed a change to branch last-successful in repository https://gitbox.apache.org/repos/asf/tvm.git from 5ed94eefad [Node] Fix structural equal path tracing pointer usage (#13082) add 71f32ca4e8

[GitHub] [tvm] wrongtest-intellif commented on pull request #13041: [Arith] Add internal NarrowPredicateExpression utility

wrongtest-intellif commented on PR #13041: URL: https://github.com/apache/tvm/pull/13041#issuecomment-1279667610 > `0 <= f < 2)`, can be narrowed to the expression `(0 <= i+0) && (i+2 < 16)` Hi~ I feel a bit confused about here: when `f == 0`, the `i` could take value in range `[0,

[tvm] branch main updated (71f32ca4e8 -> ec5c692148)

This is an automated email from the ASF dual-hosted git repository. masahi pushed a change to branch main in repository https://gitbox.apache.org/repos/asf/tvm.git from 71f32ca4e8 [MetaSchedule][UX] Support Interactive Performance Table Printing in Notebook (#13006) add ec5c692148 Add

[GitHub] [tvm] masahi merged pull request #13087: Add include directory for OpenBLAS on RedHat

masahi merged PR #13087: URL: https://github.com/apache/tvm/pull/13087 -- 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:

[GitHub] [tvm] LRY89757 commented on issue #13015: [Bug] ERROR: expect TVM_VENV env var to be set

LRY89757 commented on issue #13015: URL: https://github.com/apache/tvm/issues/13015#issuecomment-1279651417 Problem Solved? I also meet the problem. -- 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

[GitHub] [tvm] zxybazh commented on a diff in pull request #13084: [MetaSchedule] Remove Logging for Multithread Postproc Application

zxybazh commented on code in PR #13084: URL: https://github.com/apache/tvm/pull/13084#discussion_r996145902 ## src/meta_schedule/utils.h: ## @@ -318,14 +318,16 @@ struct ThreadedTraceApply { for (int i = 0; i < n_; ++i) { Item& item = items_[i]; + bool

[GitHub] [tvm] zxybazh commented on a diff in pull request #13084: [MetaSchedule] Remove Logging for Multithread Postproc Application

zxybazh commented on code in PR #13084: URL: https://github.com/apache/tvm/pull/13084#discussion_r996145902 ## src/meta_schedule/utils.h: ## @@ -318,14 +318,16 @@ struct ThreadedTraceApply { for (int i = 0; i < n_; ++i) { Item& item = items_[i]; + bool

[tvm] branch main updated: [MetaSchedule][UX] Support Interactive Performance Table Printing in Notebook (#13006)

This is an automated email from the ASF dual-hosted git repository. ruihangl 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 71f32ca4e8 [MetaSchedule][UX] Support Interactive

[GitHub] [tvm] MasterJH5574 merged pull request #13006: [MetaSchedule][UX] Support Interactive Performance Table Printing in Notebook

MasterJH5574 merged PR #13006: URL: https://github.com/apache/tvm/pull/13006 -- 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:

[GitHub] [tvm] MasterJH5574 commented on a diff in pull request #13006: [MetaSchedule][UX] Support Interactive Performance Table Printing in Notebook

MasterJH5574 commented on code in PR #13006: URL: https://github.com/apache/tvm/pull/13006#discussion_r996244804 ## python/tvm/meta_schedule/logging.py: ## @@ -129,7 +133,7 @@ def create_loggers( "class": "logging.FileHandler", "filename": "{log_dir}/"

[tvm] branch last-successful updated (342ffb91d6 -> 5ed94eefad)

This is an automated email from the ASF dual-hosted git repository. github-bot pushed a change to branch last-successful in repository https://gitbox.apache.org/repos/asf/tvm.git from 342ffb91d6 [Hexagon]Register fast softmax schedule with default schedule (#13083) add 5eab64885a

[GitHub] [tvm] ehsanmok commented on a diff in pull request #13074: [Relay][Frontend][ONNX] Add LayerNormalization operator

ehsanmok commented on code in PR #13074: URL: https://github.com/apache/tvm/pull/13074#discussion_r996231706 ## python/tvm/relay/frontend/onnx.py: ## @@ -944,6 +946,36 @@ def _impl_v1(cls, inputs, attr, params): return Gelu._impl_v1([inp], attr, params) +class

[GitHub] [tvm] tvm-bot commented on pull request #13087: Add include directory for OpenBLAS on RedHat

tvm-bot commented on PR #13087: URL: https://github.com/apache/tvm/pull/13087#issuecomment-1279614303 Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews

[GitHub] [tvm] cottsay opened a new pull request, #13087: Add include directory for OpenBLAS on RedHat

cottsay opened a new pull request, #13087: URL: https://github.com/apache/tvm/pull/13087 RedHat distributions like Fedora and RHEL package the `cblas.h` header in `/usr/include/openblas/cblas.h`[1]. Because `cblas.h` is included without the `openblas` directory, it is necessary to ensure

[tvm] branch last-successful updated (605876e638 -> 342ffb91d6)

This is an automated email from the ASF dual-hosted git repository. github-bot pushed a change to branch last-successful in repository https://gitbox.apache.org/repos/asf/tvm.git from 605876e638 [TEST] Fix the broken VNNI MetaSchedule test (#13067) add 44c35dcd96 [TVMScript] Fix

[tvm] branch nightly-docker-update updated (293ad787d5 -> 92784f415a)

This is an automated email from the ASF dual-hosted git repository. github-bot pushed a change to branch nightly-docker-update in repository https://gitbox.apache.org/repos/asf/tvm.git omit 293ad787d5 [ci][docker] Nightly Docker image update add f232272e75 [TIR] Refactor NarrowDataType

[GitHub] [tvm-rfcs] tkonolige commented on a diff in pull request #92: Tvm explorer infrastructure

tkonolige commented on code in PR #92: URL: https://github.com/apache/tvm-rfcs/pull/92#discussion_r996220676 ## rfcs/0092-TVM-Explorer-Infrastructure.md: ## @@ -0,0 +1,699 @@ +- Feature Name: TVM Explorer Infrastructure +- Start Date: Sep 1, 2022 +- RFC PR:

[tvm] branch main updated (5eab64885a -> 5ed94eefad)

This is an automated email from the ASF dual-hosted git repository. masahi pushed a change to branch main in repository https://gitbox.apache.org/repos/asf/tvm.git from 5eab64885a [ROOFLINE] Add support for different dtypes (#13003) add 5ed94eefad [Node] Fix structural equal path

[GitHub] [tvm] masahi merged pull request #13082: [Node] Fix structural equal path tracing pointer usage

masahi merged PR #13082: URL: https://github.com/apache/tvm/pull/13082 -- 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:

[GitHub] [tvm] tvm-bot commented on pull request #13086: [Draft][Relay] Add name sanitization to Id

tvm-bot commented on PR #13086: URL: https://github.com/apache/tvm/pull/13086#issuecomment-1279551479 Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews

[GitHub] [tvm] mehrdadh opened a new pull request, #13086: [Draft][Relay] Add name sanitization to Id

mehrdadh opened a new pull request, #13086: URL: https://github.com/apache/tvm/pull/13086 Just opening for testing on CI -- 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

[GitHub] [tvm] tvm-bot commented on pull request #13085: [TIR] Allow IndexMap applied to arguments with different dtypes

tvm-bot commented on PR #13085: URL: https://github.com/apache/tvm/pull/13085#issuecomment-1279550622 Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews

[GitHub] [tvm] vinx13 opened a new pull request, #13085: [TIR] Allow IndexMap applied to arguments with different dtypes

vinx13 opened a new pull request, #13085: URL: https://github.com/apache/tvm/pull/13085 cc @Lunderberg @Hzfengsy -- 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

[tvm] branch main updated (342ffb91d6 -> 5eab64885a)

This is an automated email from the ASF dual-hosted git repository. andrewzhaoluo pushed a change to branch main in repository https://gitbox.apache.org/repos/asf/tvm.git from 342ffb91d6 [Hexagon]Register fast softmax schedule with default schedule (#13083) add 5eab64885a [ROOFLINE]

[GitHub] [tvm] AndrewZhaoLuo merged pull request #13003: [ROOFLINE] Add support for different dtypes

AndrewZhaoLuo merged PR #13003: URL: https://github.com/apache/tvm/pull/13003 -- 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:

[GitHub] [tvm] AndrewZhaoLuo commented on a diff in pull request #13074: [Relay][Frontend][ONNX] Add LayerNormalization operator

AndrewZhaoLuo commented on code in PR #13074: URL: https://github.com/apache/tvm/pull/13074#discussion_r996184174 ## python/tvm/relay/frontend/onnx.py: ## @@ -944,6 +946,36 @@ def _impl_v1(cls, inputs, attr, params): return Gelu._impl_v1([inp], attr, params) +class

[GitHub] [tvm] AndrewZhaoLuo commented on a diff in pull request #13074: [Relay][Frontend][ONNX] Add LayerNormalization operator

AndrewZhaoLuo commented on code in PR #13074: URL: https://github.com/apache/tvm/pull/13074#discussion_r996196092 ## python/tvm/relay/frontend/onnx.py: ## @@ -944,6 +946,36 @@ def _impl_v1(cls, inputs, attr, params): return Gelu._impl_v1([inp], attr, params) +class

[GitHub] [tvm] AndrewZhaoLuo commented on a diff in pull request #13074: [Relay][Frontend][ONNX] Add LayerNormalization operator

AndrewZhaoLuo commented on code in PR #13074: URL: https://github.com/apache/tvm/pull/13074#discussion_r996196092 ## python/tvm/relay/frontend/onnx.py: ## @@ -944,6 +946,36 @@ def _impl_v1(cls, inputs, attr, params): return Gelu._impl_v1([inp], attr, params) +class

[GitHub] [tvm] tvm-bot commented on pull request #13022: [ETHOSN] Throw error message when inference fails

tvm-bot commented on PR #13022: URL: https://github.com/apache/tvm/pull/13022#issuecomment-1279537709 Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews

[GitHub] [tvm] AndrewZhaoLuo commented on pull request #13065: [ONNX] Handle multiple imports

AndrewZhaoLuo commented on PR #13065: URL: https://github.com/apache/tvm/pull/13065#issuecomment-1279530608 PTAL @jwfromm -- 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.

[GitHub] [tvm] AndrewZhaoLuo commented on a diff in pull request #13065: [ONNX] Handle multiple imports

AndrewZhaoLuo commented on code in PR #13065: URL: https://github.com/apache/tvm/pull/13065#discussion_r996193495 ## python/tvm/relay/frontend/onnx.py: ## @@ -5906,7 +5906,16 @@ def from_onnx( graph = model.graph try: -opset_in_model =

[GitHub] [tvm] AndrewZhaoLuo commented on a diff in pull request #13065: [ONNX] Handle multiple imports

AndrewZhaoLuo commented on code in PR #13065: URL: https://github.com/apache/tvm/pull/13065#discussion_r996152294 ## python/tvm/relay/frontend/onnx.py: ## @@ -5906,7 +5906,16 @@ def from_onnx( graph = model.graph try: -opset_in_model =

[GitHub] [tvm] AndrewZhaoLuo commented on pull request #13065: [ONNX] Handle multiple imports

AndrewZhaoLuo commented on PR #13065: URL: https://github.com/apache/tvm/pull/13065#issuecomment-1279522995 @tvm-bot rerun -- 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.

[GitHub] [tvm] ehsanmok commented on a diff in pull request #13074: [Relay][Frontend][ONNX] Add LayerNormalization operator

ehsanmok commented on code in PR #13074: URL: https://github.com/apache/tvm/pull/13074#discussion_r996186639 ## python/tvm/relay/frontend/onnx.py: ## @@ -944,6 +946,36 @@ def _impl_v1(cls, inputs, attr, params): return Gelu._impl_v1([inp], attr, params) +class

[tvm] branch main updated (44c35dcd96 -> 342ffb91d6)

This is an automated email from the ASF dual-hosted git repository. masahi pushed a change to branch main in repository https://gitbox.apache.org/repos/asf/tvm.git from 44c35dcd96 [TVMScript] Fix parsing int64 loop with optional loop start (#13068) add 342ffb91d6 [Hexagon]Register

[GitHub] [tvm] masahi merged pull request #13083: [Hexagon]Register fast softmax schedule with default schedule

masahi merged PR #13083: URL: https://github.com/apache/tvm/pull/13083 -- 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:

[GitHub] [tvm] ehsanmok commented on a diff in pull request #13074: [Relay][Frontend][ONNX] Add LayerNormalization operator

ehsanmok commented on code in PR #13074: URL: https://github.com/apache/tvm/pull/13074#discussion_r996186639 ## python/tvm/relay/frontend/onnx.py: ## @@ -944,6 +946,36 @@ def _impl_v1(cls, inputs, attr, params): return Gelu._impl_v1([inp], attr, params) +class

[GitHub] [tvm] vinx13 merged pull request #13068: [TVMScript] Fix parsing int64 loop with optional loop start

vinx13 merged PR #13068: URL: https://github.com/apache/tvm/pull/13068 -- 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:

[tvm] branch main updated (605876e638 -> 44c35dcd96)

This is an automated email from the ASF dual-hosted git repository. wuwei pushed a change to branch main in repository https://gitbox.apache.org/repos/asf/tvm.git from 605876e638 [TEST] Fix the broken VNNI MetaSchedule test (#13067) add 44c35dcd96 [TVMScript] Fix parsing int64 loop

[GitHub] [tvm] AndrewZhaoLuo commented on a diff in pull request #13074: [Relay][Frontend][ONNX] Add LayerNormalization operator

AndrewZhaoLuo commented on code in PR #13074: URL: https://github.com/apache/tvm/pull/13074#discussion_r996184174 ## python/tvm/relay/frontend/onnx.py: ## @@ -944,6 +946,36 @@ def _impl_v1(cls, inputs, attr, params): return Gelu._impl_v1([inp], attr, params) +class

[GitHub] [tvm] ehsanmok commented on a diff in pull request #13074: [Relay][Frontend][ONNX] Add LayerNormalization operator

ehsanmok commented on code in PR #13074: URL: https://github.com/apache/tvm/pull/13074#discussion_r996180529 ## python/tvm/relay/frontend/onnx.py: ## @@ -944,6 +946,36 @@ def _impl_v1(cls, inputs, attr, params): return Gelu._impl_v1([inp], attr, params) +class

[GitHub] [tvm] mehrdadh commented on pull request #13083: [Hexagon]Register fast softmax schedule with default schedule

mehrdadh commented on PR #13083: URL: https://github.com/apache/tvm/pull/13083#issuecomment-1279503902 cc @masahi -- 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

[GitHub] [tvm] ehsanmok commented on a diff in pull request #13074: [Relay][Frontend][ONNX] Add LayerNormalization operator

ehsanmok commented on code in PR #13074: URL: https://github.com/apache/tvm/pull/13074#discussion_r996180529 ## python/tvm/relay/frontend/onnx.py: ## @@ -944,6 +946,36 @@ def _impl_v1(cls, inputs, attr, params): return Gelu._impl_v1([inp], attr, params) +class

[GitHub] [tvm] ehsanmok commented on a diff in pull request #13074: [Relay][Frontend][ONNX] Add LayerNormalization operator

ehsanmok commented on code in PR #13074: URL: https://github.com/apache/tvm/pull/13074#discussion_r996179074 ## python/tvm/relay/frontend/onnx.py: ## @@ -944,6 +946,36 @@ def _impl_v1(cls, inputs, attr, params): return Gelu._impl_v1([inp], attr, params) +class

[GitHub] [tvm] csullivan closed pull request #7690: [Texture support][Part 5] Graph runtime and memory planning support for 2d allocations

csullivan closed pull request #7690: [Texture support][Part 5] Graph runtime and memory planning support for 2d allocations URL: https://github.com/apache/tvm/pull/7690 -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use

[GitHub] [tvm] csullivan commented on pull request #7690: [Texture support][Part 5] Graph runtime and memory planning support for 2d allocations

csullivan commented on PR #7690: URL: https://github.com/apache/tvm/pull/7690#issuecomment-1279486741 Subsumed by https://github.com/apache/tvm/pull/11876. -- 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

[GitHub] [tvm] jverma-quic commented on pull request #12971: [Hexagon] Add support for instrumentation based profiling for Hexagon

jverma-quic commented on PR #12971: URL: https://github.com/apache/tvm/pull/12971#issuecomment-1279486743 @tmoreau89: My PR contains a .S file which is the hand written assembly code for the profiling handler for hexagon. The CI is failing as it doesn't expect .S file to be checked in. Can

[GitHub] [tvm] csullivan commented on pull request #7689: [Texture support][Part 4] Add CollectStorageInfo and CollectBufferBinds relay passes for Adreno GPU

csullivan commented on PR #7689: URL: https://github.com/apache/tvm/pull/7689#issuecomment-1279485853 Subsumed by https://github.com/apache/tvm/pull/11878. -- 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

[GitHub] [tvm] csullivan closed pull request #7689: [Texture support][Part 4] Add CollectStorageInfo and CollectBufferBinds relay passes for Adreno GPU

csullivan closed pull request #7689: [Texture support][Part 4] Add CollectStorageInfo and CollectBufferBinds relay passes for Adreno GPU URL: https://github.com/apache/tvm/pull/7689 -- This is an automated message from the Apache Git Service. To respond to the message, please log on to

[GitHub] [tvm] csullivan closed pull request #7688: [Texture support][Part 3] Support storage scope tag in graph runtime codegen, planning, runtime and compile engine

csullivan closed pull request #7688: [Texture support][Part 3] Support storage scope tag in graph runtime codegen, planning, runtime and compile engine URL: https://github.com/apache/tvm/pull/7688 -- This is an automated message from the Apache Git Service. To respond to the message, please

[GitHub] [tvm] csullivan commented on pull request #7688: [Texture support][Part 3] Support storage scope tag in graph runtime codegen, planning, runtime and compile engine

csullivan commented on PR #7688: URL: https://github.com/apache/tvm/pull/7688#issuecomment-1279484578 Subsumed by https://github.com/apache/tvm/pull/11875. -- 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

[GitHub] [tvm] AndrewZhaoLuo commented on a diff in pull request #13074: [Relay][Frontend][ONNX] Add LayerNormalization operator

AndrewZhaoLuo commented on code in PR #13074: URL: https://github.com/apache/tvm/pull/13074#discussion_r996157034 ## python/tvm/relay/frontend/onnx.py: ## @@ -944,6 +946,36 @@ def _impl_v1(cls, inputs, attr, params): return Gelu._impl_v1([inp], attr, params) +class

[GitHub] [tvm] zxybazh commented on a diff in pull request #13006: [MetaSchedule][UX] Support Interactive Performance Table Printing in Notebook

zxybazh commented on code in PR #13006: URL: https://github.com/apache/tvm/pull/13006#discussion_r996162652 ## python/tvm/meta_schedule/logging.py: ## @@ -129,7 +133,7 @@ def create_loggers( "class": "logging.FileHandler", "filename": "{log_dir}/" +

[GitHub] [tvm] zxybazh commented on a diff in pull request #13006: [MetaSchedule][UX] Support Interactive Performance Table Printing in Notebook

zxybazh commented on code in PR #13006: URL: https://github.com/apache/tvm/pull/13006#discussion_r996155339 ## python/tvm/meta_schedule/logging.py: ## @@ -93,13 +93,16 @@ def create_loggers( global_logger_name = "tvm.meta_schedule" global_logger =

[GitHub] [tvm] vinx13 commented on pull request #13069: [TIR] Fix handling of int64 extent in blockize and tensorize

vinx13 commented on PR #13069: URL: https://github.com/apache/tvm/pull/13069#issuecomment-1279464750 Also included fix for tensorize in 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 to

[GitHub] [tvm] AndrewZhaoLuo commented on a diff in pull request #13065: [ONNX] Handle multiple imports

AndrewZhaoLuo commented on code in PR #13065: URL: https://github.com/apache/tvm/pull/13065#discussion_r996152294 ## python/tvm/relay/frontend/onnx.py: ## @@ -5906,7 +5906,16 @@ def from_onnx( graph = model.graph try: -opset_in_model =

[GitHub] [tvm] jwfromm commented on a diff in pull request #13065: [ONNX] Handle multiple imports

jwfromm commented on code in PR #13065: URL: https://github.com/apache/tvm/pull/13065#discussion_r996151252 ## python/tvm/relay/frontend/onnx.py: ## @@ -5906,7 +5906,16 @@ def from_onnx( graph = model.graph try: -opset_in_model =

[GitHub] [tvm] zxybazh commented on a diff in pull request #13084: [MetaSchedule] Remove Logging for Multithread Postproc Application

zxybazh commented on code in PR #13084: URL: https://github.com/apache/tvm/pull/13084#discussion_r996145902 ## src/meta_schedule/utils.h: ## @@ -318,14 +318,16 @@ struct ThreadedTraceApply { for (int i = 0; i < n_; ++i) { Item& item = items_[i]; + bool

[GitHub] [tvm] zxybazh commented on a diff in pull request #13084: [MetaSchedule] Remove Logging for Multithread Postproc Application

zxybazh commented on code in PR #13084: URL: https://github.com/apache/tvm/pull/13084#discussion_r996145902 ## src/meta_schedule/utils.h: ## @@ -318,14 +318,16 @@ struct ThreadedTraceApply { for (int i = 0; i < n_; ++i) { Item& item = items_[i]; + bool

[tvm] branch last-successful updated (29a8f06066 -> 605876e638)

This is an automated email from the ASF dual-hosted git repository. github-bot pushed a change to branch last-successful in repository https://gitbox.apache.org/repos/asf/tvm.git from 29a8f06066 [Arith] Optional rewriting and simplification into AND of ORs (#12972) add b389d4dac4

[GitHub] [tvm] 7andrew7 commented on a diff in pull request #13084: [MetaSchedule] Remove Logging for Multithread Postproc Application

7andrew7 commented on code in PR #13084: URL: https://github.com/apache/tvm/pull/13084#discussion_r996135473 ## src/meta_schedule/utils.h: ## @@ -318,14 +318,16 @@ struct ThreadedTraceApply { for (int i = 0; i < n_; ++i) { Item& item = items_[i]; + bool

[GitHub] [tvm] tvm-bot commented on pull request #13041: [Arith] Add internal NarrowPredicateExpression utility

tvm-bot commented on PR #13041: URL: https://github.com/apache/tvm/pull/13041#issuecomment-1279444172 Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews

[GitHub] [tvm] AndrewZhaoLuo commented on a diff in pull request #13065: [ONNX] Handle multiple imports

AndrewZhaoLuo commented on code in PR #13065: URL: https://github.com/apache/tvm/pull/13065#discussion_r996116483 ## python/tvm/relay/frontend/onnx.py: ## @@ -5906,7 +5906,16 @@ def from_onnx( graph = model.graph try: -opset_in_model =

[GitHub] [tvm] AndrewZhaoLuo commented on a diff in pull request #13065: [ONNX] Handle multiple imports

AndrewZhaoLuo commented on code in PR #13065: URL: https://github.com/apache/tvm/pull/13065#discussion_r996116037 ## python/tvm/relay/frontend/onnx.py: ## @@ -5906,7 +5906,16 @@ def from_onnx( graph = model.graph try: -opset_in_model =

[GitHub] [tvm] zxybazh opened a new pull request, #13084: [MetaSchedule] Remove Logging for Multithread Postproc Application

zxybazh opened a new pull request, #13084: URL: https://github.com/apache/tvm/pull/13084 The current datatype issue #12997 could cause the postproc application to fail in massive number, causing tons of exception logging onto the screen via `LOG(WARN)`. This change removes the postproc

[GitHub] [tvm] tvm-bot commented on pull request #13084: [MetaSchedule] Remove Logging for Multithread Postproc Application

tvm-bot commented on PR #13084: URL: https://github.com/apache/tvm/pull/13084#issuecomment-1279428188 Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews

[GitHub] [tvm] jwfromm commented on a diff in pull request #13065: [ONNX] Handle multiple imports

jwfromm commented on code in PR #13065: URL: https://github.com/apache/tvm/pull/13065#discussion_r996109044 ## python/tvm/relay/frontend/onnx.py: ## @@ -5906,7 +5906,16 @@ def from_onnx( graph = model.graph try: -opset_in_model =

[GitHub] [tvm] tkonolige commented on a diff in pull request #13003: [ROOFLINE] Add support for different dtypes

tkonolige commented on code in PR #13003: URL: https://github.com/apache/tvm/pull/13003#discussion_r996099556 ## python/tvm/utils/roofline/cuda.py: ## @@ -234,3 +259,63 @@ def estimate_peak_bandwidth( b = nd.empty((blocks, 4, warp_size), dtype="float32", device=dev)

[GitHub] [tvm] jverma-quic commented on pull request #12971: [Hexagon] Add support for instrumentation based profiling for Hexagon

jverma-quic commented on PR #12971: URL: https://github.com/apache/tvm/pull/12971#issuecomment-1279397625 @tkonolige - I have made a change in codegen_hexagon.cc to ignore profile builtins for llvm versions < 15.0. This builtin is lowered into a Hexagon specific llvm intrinsic, which was

[GitHub] [tvm] lhutton1 commented on pull request #13022: [ETHOSN] Throw error message when inference fails

lhutton1 commented on PR #13022: URL: https://github.com/apache/tvm/pull/13022#issuecomment-1279395347 @tvm-bot rerun -- 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

[GitHub] [tvm] masahi commented on a diff in pull request #13080: [Relay][Hexagon] Add per-channel FixedPointMultiply operation

masahi commented on code in PR #13080: URL: https://github.com/apache/tvm/pull/13080#discussion_r996078719 ## python/tvm/topi/hexagon/tensor_intrin.py: ## @@ -73,6 +73,58 @@ def _q_multiply_shift_hexagon(op): ) +def _q_multiply_shift_per_axis_hexagon(op): +""" +

[GitHub] [tvm] masahi commented on a diff in pull request #13050: [MetaSchedule] Consolidate module hashing and equality testing

masahi commented on code in PR #13050: URL: https://github.com/apache/tvm/pull/13050#discussion_r996070811 ## src/meta_schedule/database/json_database.cc: ## @@ -67,6 +68,10 @@ void JSONFileAppendLine(const String& path, const std::string& line) { /*! \brief The default

[GitHub] [tvm] vinx13 commented on pull request #13082: [Node] Fix structural equal path tracing pointer usage

vinx13 commented on PR #13082: URL: https://github.com/apache/tvm/pull/13082#issuecomment-1279375142 it's tested in https://github.com/apache/tvm/blob/main/tests/python/unittest/test_tir_structural_equal_hash.py but somehow passed CI -- This is an automated message from the Apache Git

[GitHub] [tvm] masahi commented on a diff in pull request #13050: [MetaSchedule] Consolidate module hashing and equality testing

masahi commented on code in PR #13050: URL: https://github.com/apache/tvm/pull/13050#discussion_r996067146 ## src/meta_schedule/database/json_database.cc: ## @@ -67,6 +68,10 @@ void JSONFileAppendLine(const String& path, const std::string& line) { /*! \brief The default

[GitHub] [tvm] masahi commented on a diff in pull request #13050: [MetaSchedule] Consolidate module hashing and equality testing

masahi commented on code in PR #13050: URL: https://github.com/apache/tvm/pull/13050#discussion_r996067146 ## src/meta_schedule/database/json_database.cc: ## @@ -67,6 +68,10 @@ void JSONFileAppendLine(const String& path, const std::string& line) { /*! \brief The default

[GitHub] [tvm] masahi commented on pull request #13071: [Frontend][PyTorch]Fix keywords to canonicalize scale and zero point access for FX-quantized graphs

masahi commented on PR #13071: URL: https://github.com/apache/tvm/pull/13071#issuecomment-1279361845 @tvm-bot rerun -- 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

[GitHub] [tvm] masahi commented on pull request #13080: [Relay][Hexagon] Add per-channel FixedPointMultiply operation

masahi commented on PR #13080: URL: https://github.com/apache/tvm/pull/13080#issuecomment-1279361546 @tvm-bot rerun -- 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

[GitHub] [tvm] masahi commented on pull request #12398: [QNN][Hexagon] Disable QNN canonicalization pass

masahi commented on PR #12398: URL: https://github.com/apache/tvm/pull/12398#issuecomment-1279360914 @tvm-bot rerun -- 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

[GitHub] [tvm] leandron commented on pull request #13078: [CI] Update Docker Image tag to 20221013-060115-61c9742ea

leandron commented on PR #13078: URL: https://github.com/apache/tvm/pull/13078#issuecomment-1279352363 @tvm-bot rerun -- 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

[GitHub] [tvm] tvm-bot commented on pull request #13083: [Hexagon]Register fast softmax schedule with default schedule

tvm-bot commented on PR #13083: URL: https://github.com/apache/tvm/pull/13083#issuecomment-1279349134 Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews

[GitHub] [tvm] mehrdadh opened a new pull request, #13083: [Hexagon]Register fast softmax schedule with default schedule

mehrdadh opened a new pull request, #13083: URL: https://github.com/apache/tvm/pull/13083 This PR registers fast softmax schedule for hexagon using the default schedule. Also renames some schedule names to hexagon. cc @csullivan -- This is an automated message from the Apache

[GitHub] [tvm] Lunderberg commented on pull request #13041: [Arith] Add internal NarrowPredicateExpression utility

Lunderberg commented on PR #13041: URL: https://github.com/apache/tvm/pull/13041#issuecomment-1279320336 Rebasing onto main to get the bug fix from #13067 -- 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

[GitHub] [tvm] Lunderberg commented on pull request #13081: [TIR][Arith] Support negative coeff in ModularSet

Lunderberg commented on PR #13081: URL: https://github.com/apache/tvm/pull/13081#issuecomment-1279319828 Rebasing onto main to get the bug fix from #13067 -- 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

[tvm] branch main updated (493458e552 -> 605876e638)

This is an automated email from the ASF dual-hosted git repository. lunderberg pushed a change to branch main in repository https://gitbox.apache.org/repos/asf/tvm.git from 493458e552 [TE] Raise error for non-bijective transformation (#12926) add 605876e638 [TEST] Fix the broken VNNI

[GitHub] [tvm] Lunderberg merged pull request #13067: [TEST] Fix the broken VNNI MetaSchedule test

Lunderberg merged PR #13067: URL: https://github.com/apache/tvm/pull/13067 -- 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:

[GitHub] [tvm] Lunderberg commented on pull request #13067: [TEST] Fix the broken VNNI MetaSchedule test

Lunderberg commented on PR #13067: URL: https://github.com/apache/tvm/pull/13067#issuecomment-1279318083 Thank you, @masahi, for this bugfix! It looks like it was causes quite a lot of CI failures. -- This is an automated message from the Apache Git Service. To respond to the message,

[GitHub] [tvm] AndrewZhaoLuo commented on a diff in pull request #13065: [ONNX] Handle multiple imports

AndrewZhaoLuo commented on code in PR #13065: URL: https://github.com/apache/tvm/pull/13065#discussion_r996016254 ## python/tvm/relay/frontend/onnx.py: ## @@ -5906,7 +5906,16 @@ def from_onnx( graph = model.graph try: -opset_in_model =

[tvm] branch main updated (f232272e75 -> 493458e552)

This is an automated email from the ASF dual-hosted git repository. wuwei pushed a change to branch main in repository https://gitbox.apache.org/repos/asf/tvm.git from f232272e75 [TIR] Refactor NarrowDataType into DataTypeLegalizer (#13049) add 493458e552 [TE] Raise error for

[GitHub] [tvm] vinx13 merged pull request #12926: [TE] Raise error for non-bijective transformation

vinx13 merged PR #12926: URL: https://github.com/apache/tvm/pull/12926 -- 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:

[GitHub] [tvm] jwfromm commented on a diff in pull request #13065: [ONNX] Handle multiple imports

jwfromm commented on code in PR #13065: URL: https://github.com/apache/tvm/pull/13065#discussion_r996007222 ## python/tvm/relay/frontend/onnx.py: ## @@ -5906,7 +5906,16 @@ def from_onnx( graph = model.graph try: -opset_in_model =

[GitHub] [tvm] vinx13 opened a new pull request, #13082: [Node] Fix structural equal path tracing pointer usage

vinx13 opened a new pull request, #13082: URL: https://github.com/apache/tvm/pull/13082 This fixed usage of pointer to local variable `tracing_data`. cc @masahi -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use

[GitHub] [tvm] tvm-bot commented on pull request #13082: [Node] Fix structural equal path tracing pointer usage

tvm-bot commented on PR #13082: URL: https://github.com/apache/tvm/pull/13082#issuecomment-1279301331 Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews

[GitHub] [tvm] ehsanmok commented on a diff in pull request #13074: [Relay][Frontend][ONNX] Add LayerNormalization operator

ehsanmok commented on code in PR #13074: URL: https://github.com/apache/tvm/pull/13074#discussion_r995954213 ## python/tvm/relay/frontend/onnx.py: ## @@ -944,6 +946,36 @@ def _impl_v1(cls, inputs, attr, params): return Gelu._impl_v1([inp], attr, params) +class

[GitHub] [tvm] MasterJH5574 commented on a diff in pull request #13049: [TIR] Refactor NarrowDataType into DataTypeLegalizer

MasterJH5574 commented on code in PR #13049: URL: https://github.com/apache/tvm/pull/13049#discussion_r995949527 ## tests/cpp/data_type_rewriter_test.cc: ## @@ -0,0 +1,140 @@ +/* Review Comment: Also filename :eyes:. ## src/tir/ir/data_type_rewriter.cc:

[tvm] branch main updated (b389d4dac4 -> f232272e75)

This is an automated email from the ASF dual-hosted git repository. bohan pushed a change to branch main in repository https://gitbox.apache.org/repos/asf/tvm.git from b389d4dac4 [Torch] Fix torch contrib issues (#13061) add f232272e75 [TIR] Refactor NarrowDataType into

[GitHub] [tvm] spectrometerHBH merged pull request #13049: [TIR] Refactor NarrowDataType into DataTypeLegalizer

spectrometerHBH merged PR #13049: URL: https://github.com/apache/tvm/pull/13049 -- 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:

[GitHub] [tvm] junrushao commented on a diff in pull request #13050: [MetaSchedule] Consolidate module hashing and equality testing

junrushao commented on code in PR #13050: URL: https://github.com/apache/tvm/pull/13050#discussion_r995910678 ## src/meta_schedule/database/json_database.cc: ## @@ -67,6 +68,10 @@ void JSONFileAppendLine(const String& path, const std::string& line) { /*! \brief The default

[GitHub] [tvm] masahi commented on pull request #13067: [TEST] Fix the broken VNNI MetaSchedule test

masahi commented on PR #13067: URL: https://github.com/apache/tvm/pull/13067#issuecomment-1279178016 @tvm-bot rerun -- 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

[GitHub] [tvm] lhutton1 commented on pull request #11208: [AOT] Calculate used memory at the callsite of primitive functions

lhutton1 commented on PR #11208: URL: https://github.com/apache/tvm/pull/11208#issuecomment-1279165680 Hi @zhaoyang-star, thanks for taking a look, its great to see this pass being used elsewhere. The pass currently expects the input to be a module of primitive functions so I would suggest

[GitHub] [tvm] MasterJH5574 commented on a diff in pull request #13006: [MetaSchedule][UX] Support Interactive Performance Table Printing in Notebook

MasterJH5574 commented on code in PR #13006: URL: https://github.com/apache/tvm/pull/13006#discussion_r995886681 ## python/tvm/meta_schedule/logging.py: ## @@ -129,7 +133,7 @@ def create_loggers( "class": "logging.FileHandler", "filename": "{log_dir}/"

  1   2   >