[GitHub] [incubator-tvm] tqchen commented on a change in pull request #5913: [random] support random fill

tqchen commented on a change in pull request #5913: URL: https://github.com/apache/incubator-tvm/pull/5913#discussion_r468988185 ## File path: src/runtime/contrib/random/mt_random_engine.cc ## @@ -111,6 +115,56 @@ class RandomEngine { } } + void RandomFill(DLTensor*

[GitHub] [incubator-tvm] tqchen commented on issue #4495: Improve ANTLR Language Dependency

tqchen commented on issue #4495: URL: https://github.com/apache/incubator-tvm/issues/4495#issuecomment-672549627 https://github.com/apache/incubator-tvm/pull/6162 This is an automated message from the Apache Git Service. To

[GitHub] [incubator-tvm] tqchen closed issue #4495: Improve ANTLR Language Dependency

tqchen closed issue #4495: URL: https://github.com/apache/incubator-tvm/issues/4495 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] [incubator-tvm] cloud-mxd commented on pull request #6242: [relay][ir] add string type to relay ir

cloud-mxd commented on pull request #6242: URL: https://github.com/apache/incubator-tvm/pull/6242#issuecomment-672514812 > I suppose this series of change are really big. Would you like to add testcases for this change? No problem, I will add some test code, thank you.

[GitHub] [incubator-tvm] cloud-mxd commented on pull request #6253: fix cuda half math function is undefined: hpow, htanh

cloud-mxd commented on pull request #6253: URL: https://github.com/apache/incubator-tvm/pull/6253#issuecomment-672496307 The above code has been tested in our production environment (T4/V100) This is an automated message

[GitHub] [incubator-tvm] cloud-mxd edited a comment on pull request #6249: Revert "fix cuda half math function is undefined: hpow, htanh"

cloud-mxd edited a comment on pull request #6249: URL: https://github.com/apache/incubator-tvm/pull/6249#issuecomment-672475552 another PR: https://github.com/apache/incubator-tvm/pull/6253 cc @tqchen This is an automated

[GitHub] [incubator-tvm] cloud-mxd commented on pull request #6249: Revert "fix cuda half math function is undefined: hpow, htanh"

cloud-mxd commented on pull request #6249: URL: https://github.com/apache/incubator-tvm/pull/6249#issuecomment-672475552 another PR: https://github.com/apache/incubator-tvm/pull/6253 This is an automated message from the

[GitHub] [incubator-tvm] cloud-mxd opened a new pull request #6253: fix cuda half math function is undefined: hpow, htanh

cloud-mxd opened a new pull request #6253: URL: https://github.com/apache/incubator-tvm/pull/6253 ref: https://github.com/apache/incubator-tvm/pull/6225 add cuda arch check This is an automated message from the Apache Git

[GitHub] [incubator-tvm] siju-samuel opened a new pull request #6252: [COREML]Reduceops support added to frontend

siju-samuel opened a new pull request #6252: URL: https://github.com/apache/incubator-tvm/pull/6252 Coreml `ReduceLayerParams` support is added. - sum - prod - mean - min - max - argmax @FrozenGene Please help me to review this. TIA

[GitHub] [incubator-tvm] junrushao1994 edited a comment on pull request #6218: [Target] Creating Target from JSON-like Configuration

junrushao1994 edited a comment on pull request #6218: URL: https://github.com/apache/incubator-tvm/pull/6218#issuecomment-672413222 Per offline discussion with @comaniac: * According to the RFC, the new Target design is beyond a raw string. It supports arbitrary nesting, more data

[GitHub] [incubator-tvm] merrymercy commented on a change in pull request #6190: [Ansor][AutoTVM v2.0] Phase 1: feature extraction for cost models

merrymercy commented on a change in pull request #6190: URL: https://github.com/apache/incubator-tvm/pull/6190#discussion_r468947442 ## File path: python/tvm/auto_scheduler/feature.py ## @@ -0,0 +1,242 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [incubator-tvm] merrymercy commented on a change in pull request #6190: [Ansor][AutoTVM v2.0] Phase 1: feature extraction for cost models

merrymercy commented on a change in pull request #6190: URL: https://github.com/apache/incubator-tvm/pull/6190#discussion_r468947442 ## File path: python/tvm/auto_scheduler/feature.py ## @@ -0,0 +1,242 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [incubator-tvm] junrushao1994 commented on pull request #6218: [Target] Creating Target from JSON-like Configuration

junrushao1994 commented on pull request #6218: URL: https://github.com/apache/incubator-tvm/pull/6218#issuecomment-672413222 Per offline discussion with @comaniac: * According to the RFC, the new Target design is beyond a raw string. It supports arbitrary nesting, more data types, etc.

[GitHub] [incubator-tvm] merrymercy commented on a change in pull request #6190: [Ansor][AutoTVM v2.0] Phase 1: feature extraction for cost models

merrymercy commented on a change in pull request #6190: URL: https://github.com/apache/incubator-tvm/pull/6190#discussion_r468359834 ## File path: python/tvm/auto_scheduler/feature.py ## @@ -0,0 +1,242 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [incubator-tvm] junrushao1994 commented on a change in pull request #6218: [Target] Creating Target from JSON-like Configuration

junrushao1994 commented on a change in pull request #6218: URL: https://github.com/apache/incubator-tvm/pull/6218#discussion_r468944432 ## File path: src/target/target.cc ## @@ -30,20 +30,195 @@ #include #include +#include "../runtime/object_internal.h" + namespace tvm

[GitHub] [incubator-tvm] csullivan opened a new pull request #6251: [ONNX] Add Clip importer to handle when min/max are provided as inputs.

csullivan opened a new pull request #6251: URL: https://github.com/apache/incubator-tvm/pull/6251 This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL

[GitHub] [incubator-tvm] yangjunpro commented on a change in pull request #6190: [Ansor][AutoTVM v2.0] Phase 1: feature extraction for cost models

yangjunpro commented on a change in pull request #6190: URL: https://github.com/apache/incubator-tvm/pull/6190#discussion_r468939081 ## File path: include/tvm/auto_scheduler/feature.h ## @@ -0,0 +1,122 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + *

[GitHub] [incubator-tvm] comaniac commented on a change in pull request #6218: [Target] Creating Target from JSON-like Configuration

comaniac commented on a change in pull request #6218: URL: https://github.com/apache/incubator-tvm/pull/6218#discussion_r468942491 ## File path: src/target/target.cc ## @@ -30,20 +30,195 @@ #include #include +#include "../runtime/object_internal.h" + namespace tvm {

[GitHub] [incubator-tvm] zhiics opened a new pull request #6250: [TOPI] Fix reduction

zhiics opened a new pull request #6250: URL: https://github.com/apache/incubator-tvm/pull/6250 A small fix to cuda reduction schedule cc @icemelon9 @masahi This is an automated message from the Apache Git Service. To

[GitHub] [incubator-tvm] junrushao1994 commented on a change in pull request #6218: [Target] Creating Target from JSON-like Configuration

junrushao1994 commented on a change in pull request #6218: URL: https://github.com/apache/incubator-tvm/pull/6218#discussion_r468939010 ## File path: src/target/target.cc ## @@ -30,20 +30,195 @@ #include #include +#include "../runtime/object_internal.h" + namespace tvm

[incubator-tvm] branch master updated: Revert "fix cuda half math function is undefined: hpow, htanh (#6225)" (#6249)

This is an automated email from the ASF dual-hosted git repository. tqchen pushed a commit to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git The following commit(s) were added to refs/heads/master by this push: new 7174ac2 Revert "fix cuda half math

[GitHub] [incubator-tvm] tqchen merged pull request #6249: Revert "fix cuda half math function is undefined: hpow, htanh"

tqchen merged pull request #6249: URL: https://github.com/apache/incubator-tvm/pull/6249 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

[GitHub] [incubator-tvm] comaniac commented on a change in pull request #6218: [Target] Creating Target from JSON-like Configuration

comaniac commented on a change in pull request #6218: URL: https://github.com/apache/incubator-tvm/pull/6218#discussion_r468935069 ## File path: src/target/target.cc ## @@ -162,14 +313,149 @@ Target Target::Create(const String& target_str) { return CreateTarget(splits[0],

[GitHub] [incubator-tvm] junrushao1994 commented on a change in pull request #6218: [Target] Creating Target from JSON-like Configuration

junrushao1994 commented on a change in pull request #6218: URL: https://github.com/apache/incubator-tvm/pull/6218#discussion_r468933421 ## File path: src/target/target.cc ## @@ -30,20 +30,195 @@ #include #include +#include "../runtime/object_internal.h" + namespace tvm

[GitHub] [incubator-tvm] junrushao1994 commented on a change in pull request #6218: [Target] Creating Target from JSON-like Configuration

junrushao1994 commented on a change in pull request #6218: URL: https://github.com/apache/incubator-tvm/pull/6218#discussion_r468931440 ## File path: src/target/target.cc ## @@ -30,20 +30,195 @@ #include #include +#include "../runtime/object_internal.h" + namespace tvm

[GitHub] [incubator-tvm] junrushao1994 commented on a change in pull request #6218: [Target] Creating Target from JSON-like Configuration

junrushao1994 commented on a change in pull request #6218: URL: https://github.com/apache/incubator-tvm/pull/6218#discussion_r468930805 ## File path: src/target/target.cc ## @@ -162,14 +313,149 @@ Target Target::Create(const String& target_str) { return

[GitHub] [incubator-tvm] junrushao1994 commented on a change in pull request #6218: [Target] Creating Target from JSON-like Configuration

junrushao1994 commented on a change in pull request #6218: URL: https://github.com/apache/incubator-tvm/pull/6218#discussion_r468929183 ## File path: src/target/target.cc ## @@ -162,14 +313,149 @@ Target Target::Create(const String& target_str) { return

[GitHub] [incubator-tvm] comaniac commented on a change in pull request #6218: [Target] Creating Target from JSON-like Configuration

comaniac commented on a change in pull request #6218: URL: https://github.com/apache/incubator-tvm/pull/6218#discussion_r468900741 ## File path: src/target/target.cc ## @@ -162,14 +313,149 @@ Target Target::Create(const String& target_str) { return CreateTarget(splits[0],

[GitHub] [incubator-tvm] merrymercy commented on a change in pull request #6190: [Ansor][AutoTVM v2.0] Phase 1: feature extraction for cost models

merrymercy commented on a change in pull request #6190: URL: https://github.com/apache/incubator-tvm/pull/6190#discussion_r468927343 ## File path: python/tvm/auto_scheduler/feature.py ## @@ -0,0 +1,242 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [incubator-tvm] merrymercy commented on a change in pull request #6190: [Ansor][AutoTVM v2.0] Phase 1: feature extraction for cost models

merrymercy commented on a change in pull request #6190: URL: https://github.com/apache/incubator-tvm/pull/6190#discussion_r468927281 ## File path: python/tvm/auto_scheduler/feature.py ## @@ -0,0 +1,242 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [incubator-tvm] jroesch merged pull request #6162: [Parser] Parser 2.0 part 2

jroesch merged pull request #6162: URL: https://github.com/apache/incubator-tvm/pull/6162 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

[incubator-tvm] branch master updated (75b8318 -> fa2213f)

This is an automated email from the ASF dual-hosted git repository. jroesch pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from 75b8318 [Ansor][AutoTVM v2.0] Phase 2: Basic CPU Sketch Search Policy (#6184) add fa2213f [Parser]

[GitHub] [incubator-tvm] tqchen commented on pull request #6190: [Ansor][AutoTVM v2.0] Phase 1: feature extraction for cost models

tqchen commented on pull request #6190: URL: https://github.com/apache/incubator-tvm/pull/6190#issuecomment-672337634 @merrymercy please fix the conflict This is an automated message from the Apache Git Service. To respond

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #6078: [Autodiff] Optimize and eliminate the Jacobian tensor for te.autodiff

tqchen commented on a change in pull request #6078: URL: https://github.com/apache/incubator-tvm/pull/6078#discussion_r468908098 ## File path: include/tvm/node/container.h ## @@ -1287,6 +1287,18 @@ class Map : public ObjectRef { data_ = other.data_; return *this;

[GitHub] [incubator-tvm] weberlo commented on pull request #5940: Add Quantize/Dequantize Partitioning

weberlo commented on pull request #5940: URL: https://github.com/apache/incubator-tvm/pull/5940#issuecomment-672323092 > @weberlo Will this affect the original pipeline when the config `partition_conversions` is `disabled`? @ZihengJiang It won't affect the original pipeline, since

[GitHub] [incubator-tvm] tmoreau89 commented on pull request #5940: Add Quantize/Dequantize Partitioning

tmoreau89 commented on pull request #5940: URL: https://github.com/apache/incubator-tvm/pull/5940#issuecomment-672314270 Nice work @weberlo, do can we add a `partition_conversions=disabled` unit test as well? This is an

[GitHub] [incubator-tvm] junrushao1994 commented on pull request #6218: [Target] Creating Target from JSON-like Configuration

junrushao1994 commented on pull request #6218: URL: https://github.com/apache/incubator-tvm/pull/6218#issuecomment-672304325 This PR is ready for review. Please take a look. Thanks! This is an automated message from the

[GitHub] [incubator-tvm] ZihengJiang commented on pull request #5940: Add Quantize/Dequantize Partitioning

ZihengJiang commented on pull request #5940: URL: https://github.com/apache/incubator-tvm/pull/5940#issuecomment-672284273 @weberlo Will this affect the original pipeline when the config `partition_conversions` is `disabled`?

[GitHub] [incubator-tvm] weberlo commented on pull request #5940: Add Quantize/Dequantize Partitioning

weberlo commented on pull request #5940: URL: https://github.com/apache/incubator-tvm/pull/5940#issuecomment-672282100 @ZihengJiang I've rebased and converted the datatype collector pass into C++, but I won't be prioritizing C++ conversion for the other visitors for the next few weeks.

[incubator-tvm] branch master updated (db6e0c1 -> 75b8318)

This is an automated email from the ASF dual-hosted git repository. lmzheng pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from db6e0c1 [JVM] Support overriding RPCWatchdog termination behavior on Android and other platforms (#6216)

[GitHub] [incubator-tvm] merrymercy merged pull request #6184: [Ansor][AutoTVM v2.0] Phase 2: Basic CPU Sketch Search Policy

merrymercy merged pull request #6184: URL: https://github.com/apache/incubator-tvm/pull/6184 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] [incubator-tvm] merrymercy commented on pull request #6184: [Ansor][AutoTVM v2.0] Phase 2: Basic CPU Sketch Search Policy

merrymercy commented on pull request #6184: URL: https://github.com/apache/incubator-tvm/pull/6184#issuecomment-672269797 @comaniac @junrushao1994 Wait for your approval and I will merge this This is an automated message

[GitHub] [incubator-tvm] merrymercy edited a comment on pull request #6190: [Ansor][AutoTVM v2.0] Phase 1: feature extraction for cost models

merrymercy edited a comment on pull request #6190: URL: https://github.com/apache/incubator-tvm/pull/6190#issuecomment-672266466 I organized the features into 5 groups. ``` // Group 1: Computation related features // Group 2: Buffer access related features (per buffer) //

[GitHub] [incubator-tvm] merrymercy edited a comment on pull request #6190: [Ansor][AutoTVM v2.0] Phase 1: feature extraction for cost models

merrymercy edited a comment on pull request #6190: URL: https://github.com/apache/incubator-tvm/pull/6190#issuecomment-672266466 I organized the features into 5 groups. ``` // Group 1: Computation related features // Group 2: Buffer access related features (per buffer) //

[GitHub] [incubator-tvm] merrymercy edited a comment on pull request #6190: [Ansor][AutoTVM v2.0] Phase 1: feature extraction for cost models

merrymercy edited a comment on pull request #6190: URL: https://github.com/apache/incubator-tvm/pull/6190#issuecomment-672266466 I organized the features into 5 groups. ``` // Group 1: Computation related features // Group 2: Buffer access related features (per buffer) //

[GitHub] [incubator-tvm] merrymercy edited a comment on pull request #6190: [Ansor][AutoTVM v2.0] Phase 1: feature extraction for cost models

merrymercy edited a comment on pull request #6190: URL: https://github.com/apache/incubator-tvm/pull/6190#issuecomment-672266466 I organized the features into 5 groups. ``` // Group 1: Computation related features // Group 2: Buffer access related features (per buffer) //

[GitHub] [incubator-tvm] merrymercy edited a comment on pull request #6190: [Ansor][AutoTVM v2.0] Phase 1: feature extraction for cost models

merrymercy edited a comment on pull request #6190: URL: https://github.com/apache/incubator-tvm/pull/6190#issuecomment-672266466 I organized the features into 5 groups. ``` // Group 1: Computation related features // Group 2: Buffer access related features (per buffer) //

[GitHub] [incubator-tvm] merrymercy edited a comment on pull request #6190: [Ansor][AutoTVM v2.0] Phase 1: feature extraction for cost models

merrymercy edited a comment on pull request #6190: URL: https://github.com/apache/incubator-tvm/pull/6190#issuecomment-672266466 I organized the features into 5 groups. ``` // Group 1: Computation related features // Group 2: Buffer access related features (per buffer) //

[GitHub] [incubator-tvm] merrymercy commented on pull request #6190: [Ansor][AutoTVM v2.0] Phase 1: feature extraction for cost models

merrymercy commented on pull request #6190: URL: https://github.com/apache/incubator-tvm/pull/6190#issuecomment-672266466 I organized the features into 5 groups. ``` // Group 1: Computation related features // Group 2: Buffer access related features (per buffer) // Group

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #6222: [BYOC][ETHOSN] Introduce the Ethos-N BYOC integration

zhiics commented on a change in pull request #6222: URL: https://github.com/apache/incubator-tvm/pull/6222#discussion_r468844000 ## File path: tests/python/contrib/test_ethosn/infrastructure.py ## @@ -0,0 +1,225 @@ +# Licensed to the Apache Software Foundation (ASF) under one

[GitHub] [incubator-tvm] manupa-arm commented on pull request #6219: [Runtime][WIP] Add prototype Relay AoT compiler directly into TVM

manupa-arm commented on pull request #6219: URL: https://github.com/apache/incubator-tvm/pull/6219#issuecomment-672259003 @MarisaKirisame , thanks for the clarification! This is an automated message from

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #6222: [BYOC][ETHOSN] Introduce the Ethos-N BYOC integration

zhiics commented on a change in pull request #6222: URL: https://github.com/apache/incubator-tvm/pull/6222#discussion_r468838305 ## File path: src/runtime/contrib/ethosn/ethosn_runtime.h ## @@ -0,0 +1,111 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one +

[incubator-tvm] branch master updated (12da324 -> db6e0c1)

This is an automated email from the ASF dual-hosted git repository. tqchen pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from 12da324 Fix division range estimation error in simplifier (#6244) add db6e0c1 [JVM] Support overriding

[GitHub] [incubator-tvm] tqchen merged pull request #6216: [JVM] Support overriding RPCWatchdog termination behavior on Android and other platforms

tqchen merged pull request #6216: URL: https://github.com/apache/incubator-tvm/pull/6216 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

[GitHub] [incubator-tvm] csullivan commented on pull request #6216: [JVM] Support overriding RPCWatchdog termination behavior on Android and other platforms

csullivan commented on pull request #6216: URL: https://github.com/apache/incubator-tvm/pull/6216#issuecomment-672247353 @tmoreau89, @tqchen, if you have time please review the updates. Thanks! This is an automated message

[GitHub] [incubator-tvm] junrushao1994 commented on pull request #6242: [relay][ir] add string type to relay ir

junrushao1994 commented on pull request #6242: URL: https://github.com/apache/incubator-tvm/pull/6242#issuecomment-672241664 I suppose this series of change are really big. Would you like to add testcases for this change?

[GitHub] [incubator-tvm] tqchen commented on pull request #6249: Revert "fix cuda half math function is undefined: hpow, htanh"

tqchen commented on pull request #6249: URL: https://github.com/apache/incubator-tvm/pull/6249#issuecomment-672180416 cc @jroesch This is an automated message from the Apache Git Service. To respond to the message, please

[GitHub] [incubator-tvm] tqchen edited a comment on pull request #6249: Revert "fix cuda half math function is undefined: hpow, htanh"

tqchen edited a comment on pull request #6249: URL: https://github.com/apache/incubator-tvm/pull/6249#issuecomment-672179856 cc @cloud-mxd due to the CI problem as in https://ci.tvm.ai/blue/organizations/jenkins/tvm/detail/PR-6162/29/pipeline/ Please feel free to send another PR and

[GitHub] [incubator-tvm] tqchen commented on pull request #6249: Revert "fix cuda half math function is undefined: hpow, htanh"

tqchen commented on pull request #6249: URL: https://github.com/apache/incubator-tvm/pull/6249#issuecomment-672179856 cc @cloud-mxd due to the CI problem defined in https://ci.tvm.ai/blue/organizations/jenkins/tvm/detail/PR-6162/29/pipeline/ Please feel free to send another PR and

[incubator-tvm] branch revert-6225-dev_mxd_fix_cuda_fp16 created (now 45415b3)

This is an automated email from the ASF dual-hosted git repository. tqchen pushed a change to branch revert-6225-dev_mxd_fix_cuda_fp16 in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. at 45415b3 Revert "fix cuda half math function is undefined: hpow, htanh (#6225)"

[GitHub] [incubator-tvm] tqchen opened a new pull request #6249: Revert "fix cuda half math function is undefined: hpow, htanh"

tqchen opened a new pull request #6249: URL: https://github.com/apache/incubator-tvm/pull/6249 Reverts apache/incubator-tvm#6225 This is an automated message from the Apache Git Service. To respond to the message, please log

[GitHub] [incubator-tvm] mbaret commented on pull request #6222: [BYOC][ETHOSN] Introduce the Ethos-N BYOC integration

mbaret commented on pull request #6222: URL: https://github.com/apache/incubator-tvm/pull/6222#issuecomment-672137931 > It looks that this is a different from C source module and the json runtime module. Could you elaborate a bit why those two don't fit? The Ethos-N compiler

[GitHub] [incubator-tvm] mbaret commented on a change in pull request #6222: [BYOC][ETHOSN] Introduce the Ethos-N BYOC integration

mbaret commented on a change in pull request #6222: URL: https://github.com/apache/incubator-tvm/pull/6222#discussion_r468752615 ## File path: tests/python/contrib/test_ethosn/infrastructure.py ## @@ -0,0 +1,225 @@ +# Licensed to the Apache Software Foundation (ASF) under one

[GitHub] [incubator-tvm] mbaret commented on a change in pull request #6222: [BYOC][ETHOSN] Introduce the Ethos-N BYOC integration

mbaret commented on a change in pull request #6222: URL: https://github.com/apache/incubator-tvm/pull/6222#discussion_r468750593 ## File path: src/relay/backend/contrib/ethosn/capabilities.h ## @@ -0,0 +1,81 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one

[GitHub] [incubator-tvm] mbaret commented on a change in pull request #6222: [BYOC][ETHOSN] Introduce the Ethos-N BYOC integration

mbaret commented on a change in pull request #6222: URL: https://github.com/apache/incubator-tvm/pull/6222#discussion_r468749731 ## File path: src/runtime/contrib/ethosn/ethosn_runtime.h ## @@ -0,0 +1,111 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one +

[GitHub] [incubator-tvm] mbaret commented on a change in pull request #6222: [BYOC][ETHOSN] Introduce the Ethos-N BYOC integration

mbaret commented on a change in pull request #6222: URL: https://github.com/apache/incubator-tvm/pull/6222#discussion_r468748218 ## File path: src/runtime/contrib/ethosn/ethosn_runtime.cc ## @@ -0,0 +1,146 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one +

[GitHub] [incubator-tvm] mbaret commented on a change in pull request #6222: [BYOC][ETHOSN] Introduce the Ethos-N BYOC integration

mbaret commented on a change in pull request #6222: URL: https://github.com/apache/incubator-tvm/pull/6222#discussion_r468745993 ## File path: python/tvm/relay/op/contrib/ethosn.py ## @@ -0,0 +1,90 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [incubator-tvm] MarisaKirisame commented on pull request #6219: [Runtime][WIP] Add prototype Relay AoT compiler directly into TVM

MarisaKirisame commented on pull request #6219: URL: https://github.com/apache/incubator-tvm/pull/6219#issuecomment-672111705 @manupa-arm the primitive function is still lowered to TIR - we only compile Relay fragment to C++. This is in accordance to how Relay had work for Interpreter/VM

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #6222: [BYOC][ETHOSN] Introduce the Ethos-N BYOC integration

zhiics commented on a change in pull request #6222: URL: https://github.com/apache/incubator-tvm/pull/6222#discussion_r468690336 ## File path: cmake/modules/contrib/EthosN.cmake ## @@ -0,0 +1,58 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [incubator-tvm] jwfromm commented on a change in pull request #6190: [Ansor][AutoTVM v2.0] Phase 1: feature extraction for cost models

jwfromm commented on a change in pull request #6190: URL: https://github.com/apache/incubator-tvm/pull/6190#discussion_r468701334 ## File path: tests/python/unittest/test_auto_scheduler_feature.py ## @@ -0,0 +1,149 @@ +# Licensed to the Apache Software Foundation (ASF) under

[incubator-tvm] branch master updated (2845329 -> 12da324)

This is an automated email from the ASF dual-hosted git repository. tqchen pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from 2845329 [TFLite] Implemented EXPAND_DIMS Operator for TFLite. (#6243) add 12da324 Fix division range

[GitHub] [incubator-tvm] tqchen merged pull request #6244: Fix division range estimation error in simplifier

tqchen merged pull request #6244: URL: https://github.com/apache/incubator-tvm/pull/6244 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

[GitHub] [incubator-tvm] tqchen commented on pull request #6244: Fix division range estimation error in simplifier

tqchen commented on pull request #6244: URL: https://github.com/apache/incubator-tvm/pull/6244#issuecomment-672021229 Thanks @kparzysz-quic ! This is an automated message from the Apache Git Service. To respond to the

[GitHub] [incubator-tvm] quic-sanirudh commented on pull request #6138: Add `init` member to ReduceNode

quic-sanirudh commented on pull request #6138: URL: https://github.com/apache/incubator-tvm/pull/6138#issuecomment-671992636 > Oh, i meant test cases that use this feature to compile a reduction with init value like those in `tests/python/integration` Ah okay, thanks for the

[GitHub] [incubator-tvm] tqchen commented on pull request #6138: Add `init` member to ReduceNode

tqchen commented on pull request #6138: URL: https://github.com/apache/incubator-tvm/pull/6138#issuecomment-671987519 Oh, i meant test cases that use this feature to compile a reduction with init value like those in `tests/python/integration`

[GitHub] [incubator-tvm] lhutton1 opened a new pull request #6248: [BYOC][ACL] Improved pooling support

lhutton1 opened a new pull request #6248: URL: https://github.com/apache/incubator-tvm/pull/6248 This patch adds support for various pooling operators, namely: average pool 2d, global max pool 2d, global average pool 2d and l2 pooling (an equivalent combination of relay operators).

[GitHub] [incubator-tvm] quic-sanirudh edited a comment on pull request #6138: Add `init` member to ReduceNode

quic-sanirudh edited a comment on pull request #6138: URL: https://github.com/apache/incubator-tvm/pull/6138#issuecomment-671882417 Thanks @tqchen for the suggestion. I'll work on adding the rfactor support and update the PR once its done. Also, could you explain what you meant by

[GitHub] [incubator-tvm] manupa-arm commented on pull request #6219: [Runtime][WIP] Add prototype Relay AoT compiler directly into TVM

manupa-arm commented on pull request #6219: URL: https://github.com/apache/incubator-tvm/pull/6219#issuecomment-671903407 @slyubomirsky Thanks for the work! -- Some very high-level comments. IIUC, this is bypassing the TIR lowering as it stands today. Thus, possibly losing the

[GitHub] [incubator-tvm] quic-sanirudh commented on pull request #6138: Add `init` member to ReduceNode

quic-sanirudh commented on pull request #6138: URL: https://github.com/apache/incubator-tvm/pull/6138#issuecomment-671882417 Thanks @tqchen for the suggestion. I'll work on adding the rfactor support and update the PR once its done. Could you explain what you meant by adding

[GitHub] [incubator-tvm] leandron commented on a change in pull request #6112: TVMC - a command line driver for TVM (Part 1)

leandron commented on a change in pull request #6112: URL: https://github.com/apache/incubator-tvm/pull/6112#discussion_r468454560 ## File path: python/tvm/driver/tvmc/main.py ## @@ -0,0 +1,90 @@ +#!/usr/bin/env python + +# Licensed to the Apache Software Foundation (ASF)

[GitHub] [incubator-tvm] jroesch commented on pull request #6162: [Parser] Parser 2.0 part 2

jroesch commented on pull request #6162: URL: https://github.com/apache/incubator-tvm/pull/6162#issuecomment-671818745 @tqchen this should be gtg, looks like I got passed the last few CPU tests. This is an automated message

[GitHub] [incubator-tvm] FrozenGene commented on pull request #6243: [TFLite] Implemented EXPAND_DIMS Operator for TFLite.

FrozenGene commented on pull request #6243: URL: https://github.com/apache/incubator-tvm/pull/6243#issuecomment-671796154 Thanks @jainris This is an automated message from the Apache Git Service. To respond to the message,

[incubator-tvm] branch master updated: [TFLite] Implemented EXPAND_DIMS Operator for TFLite. (#6243)

This is an automated email from the ASF dual-hosted git repository. zhaowu pushed a commit to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git The following commit(s) were added to refs/heads/master by this push: new 2845329 [TFLite] Implemented

[GitHub] [incubator-tvm] FrozenGene merged pull request #6243: [TFLite] Implemented EXPAND_DIMS Operator for TFLite.

FrozenGene merged pull request #6243: URL: https://github.com/apache/incubator-tvm/pull/6243 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] [incubator-tvm] FrozenGene edited a comment on pull request #5913: [random] support random fill

FrozenGene edited a comment on pull request #5913: URL: https://github.com/apache/incubator-tvm/pull/5913#issuecomment-671789877 > > @FrozenGene Please followup. It is okay to do the path `CPU@remote_device -> GPU@remote_device` for now, as long as there is no RPC communication cost (i.e.

[GitHub] [incubator-tvm] FrozenGene commented on pull request #5913: [random] support random fill

FrozenGene commented on pull request #5913: URL: https://github.com/apache/incubator-tvm/pull/5913#issuecomment-671789877 > > @FrozenGene Please followup. It is okay to do the path `CPU@remote_device -> GPU@remote_device` for now, as long as there is no RPC communication cost (i.e. no

[GitHub] [incubator-tvm] FrozenGene edited a comment on pull request #6229: [RPC] Update build support for cross compiling apps/cpp_rpc with OpenCL

FrozenGene edited a comment on pull request #6229: URL: https://github.com/apache/incubator-tvm/pull/6229#issuecomment-671787510 Thanks @csullivan I've verified it and it works. This is an automated message from the Apache

[GitHub] [incubator-tvm] FrozenGene commented on pull request #6229: [RPC] Update build support for cross compiling apps/cpp_rpc with OpenCL

FrozenGene commented on pull request #6229: URL: https://github.com/apache/incubator-tvm/pull/6229#issuecomment-671787510 Thanks @csullivan I verified it and it works. This is an automated message from the Apache Git

[GitHub] [incubator-tvm] FrozenGene merged pull request #6229: [RPC] Update build support for cross compiling apps/cpp_rpc with OpenCL

FrozenGene merged pull request #6229: URL: https://github.com/apache/incubator-tvm/pull/6229 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

[incubator-tvm] branch master updated (ee33056 -> 14f4efe)

This is an automated email from the ASF dual-hosted git repository. zhaowu pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from ee33056 [Topi,x86] Split MKL from BLAS. (#6182) add 14f4efe [RPC] Update build support for cross

[GitHub] [incubator-tvm] jcf94 commented on pull request #6184: [Ansor][AutoTVM v2.0] Phase 2: Basic CPU Sketch Search Policy

jcf94 commented on pull request #6184: URL: https://github.com/apache/incubator-tvm/pull/6184#issuecomment-671763210 > Overall LGTM, but I'd like to raise the discussion about the file organization for search policy. Now `sketch_search_policy.cc` has about one thousand line and it might

[GitHub] [incubator-tvm] merrymercy commented on a change in pull request #6190: [Ansor][AutoTVM v2.0] Phase 1: feature extraction for cost models

merrymercy commented on a change in pull request #6190: URL: https://github.com/apache/incubator-tvm/pull/6190#discussion_r468359065 ## File path: python/tvm/auto_scheduler/feature.py ## @@ -0,0 +1,242 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [incubator-tvm] merrymercy commented on a change in pull request #6190: [Ansor][AutoTVM v2.0] Phase 1: feature extraction for cost models

merrymercy commented on a change in pull request #6190: URL: https://github.com/apache/incubator-tvm/pull/6190#discussion_r468359834 ## File path: python/tvm/auto_scheduler/feature.py ## @@ -0,0 +1,242 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [incubator-tvm] merrymercy commented on a change in pull request #6190: [Ansor][AutoTVM v2.0] Phase 1: feature extraction for cost models

merrymercy commented on a change in pull request #6190: URL: https://github.com/apache/incubator-tvm/pull/6190#discussion_r468359834 ## File path: python/tvm/auto_scheduler/feature.py ## @@ -0,0 +1,242 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [incubator-tvm] merrymercy commented on a change in pull request #6190: [Ansor][AutoTVM v2.0] Phase 1: feature extraction for cost models

merrymercy commented on a change in pull request #6190: URL: https://github.com/apache/incubator-tvm/pull/6190#discussion_r468359834 ## File path: python/tvm/auto_scheduler/feature.py ## @@ -0,0 +1,242 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [incubator-tvm] merrymercy commented on a change in pull request #6190: [Ansor][AutoTVM v2.0] Phase 1: feature extraction for cost models

merrymercy commented on a change in pull request #6190: URL: https://github.com/apache/incubator-tvm/pull/6190#discussion_r468359065 ## File path: python/tvm/auto_scheduler/feature.py ## @@ -0,0 +1,242 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [incubator-tvm] jcf94 commented on a change in pull request #6184: [Ansor][AutoTVM v2.0] Phase 2: Basic CPU Sketch Search Policy

jcf94 commented on a change in pull request #6184: URL: https://github.com/apache/incubator-tvm/pull/6184#discussion_r468346294 ## File path: tests/python/unittest/test_auto_scheduler_sketch_generation.py ## @@ -0,0 +1,107 @@ +# Licensed to the Apache Software Foundation (ASF)