[GitHub] [incubator-tvm] maheshambule commented on pull request #5486: [TFLITE]Select op support for tflite frontend

maheshambule commented on pull request #5486: URL: https://github.com/apache/incubator-tvm/pull/5486#issuecomment-625091810 > LGTM. @siju-samuel After thinking about this pr, I think we should make `get_expr` and `exp_tab.new_const` be private and only public `get_tensor_expr`. Other

[incubator-tvm] branch revert-5486-tflite_select created (now c238287)

This is an automated email from the ASF dual-hosted git repository. masahi pushed a change to branch revert-5486-tflite_select in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. at c238287 Revert "[TFLITE]Select op support for tflite frontend (#5486)" This branch

[incubator-tvm] 01/01: Revert "[TFLITE]Select op support for tflite frontend (#5486)"

This is an automated email from the ASF dual-hosted git repository. masahi pushed a commit to branch revert-5486-tflite_select in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git commit c2382871eea8dca7b7c82044e93045cda53e0352 Author: masahi AuthorDate: Thu May 7 17:04:36 2020

[GitHub] [incubator-tvm] FrozenGene commented on pull request #5486: [TFLITE]Select op support for tflite frontend

FrozenGene commented on pull request #5486: URL: https://github.com/apache/incubator-tvm/pull/5486#issuecomment-625080689 Thanks @siju-samuel @u99127 merged now. This is an automated message from the Apache Git Service. To

[GitHub] [incubator-tvm] wpan11nv commented on a change in pull request #5498: [Optimization] Warp level reduction support for CUDA

wpan11nv commented on a change in pull request #5498: URL: https://github.com/apache/incubator-tvm/pull/5498#discussion_r421294707 ## File path: src/tir/transforms/lower_warp_memory.cc ## @@ -265,10 +265,11 @@ class WarpAccessRewriter : protected StmtExprMutator {

[GitHub] [incubator-tvm] FrozenGene commented on pull request #5486: [TFLITE]Select op support for tflite frontend

FrozenGene commented on pull request #5486: URL: https://github.com/apache/incubator-tvm/pull/5486#issuecomment-625080456 LGTM. @siju-samuel After thinking about this pr, I think we should make `get_expr` and `exp_tab.new_const` be private and only public `get_tensor_expr`. Other places

[incubator-tvm] branch master updated (900254d -> 149965a)

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 900254d Fix an issue with Upsampling and update one test to hit the broken usecase (#5530) add 149965a

[GitHub] [incubator-tvm] cchung100m commented on a change in pull request #5511: [AutoTVM][TOPI] AutoTVM incorrect measurement

cchung100m commented on a change in pull request #5511: URL: https://github.com/apache/incubator-tvm/pull/5511#discussion_r421266463 ## File path: topi/python/topi/mali/conv2d.py ## @@ -138,20 +138,15 @@ def _schedule_spatial_pack(cfg, s, output, conv, data_vec, kernel_vec):

[GitHub] [incubator-tvm] wsl-inspur commented on pull request #5485: [TOPI][Winograd] Optimization of Conv2d Winograd algorithm on Tensor …

wsl-inspur commented on pull request #5485: URL: https://github.com/apache/incubator-tvm/pull/5485#issuecomment-625091214 @FrozenGene We made the following tests to go through all the layouts, Layout_1(the same in this PR) input_tile = (P, CI, alpha, alpha) data_pack =

[GitHub] [incubator-tvm] siju-samuel commented on pull request #5486: [TFLITE]Select op support for tflite frontend

siju-samuel commented on pull request #5486: URL: https://github.com/apache/incubator-tvm/pull/5486#issuecomment-625084251 > LGTM. @siju-samuel After thinking about this pr, I think we should make get_expr and exp_tab.new_const be private and only public get_tensor_expr. Other places use

[GitHub] [incubator-tvm] wsl-inspur edited a comment on pull request #5485: [TOPI][Winograd] Optimization of Conv2d Winograd algorithm on Tensor …

wsl-inspur edited a comment on pull request #5485: URL: https://github.com/apache/incubator-tvm/pull/5485#issuecomment-625091214 @FrozenGene We made the following tests to go through all the layouts, Layout_1(the same in this PR) input_tile = (P, CI, alpha, alpha)

[GitHub] [incubator-tvm] ANSHUMAN87 commented on pull request #5510: [FRONTEND][TFLite] Fully connected op conversion made in sync with TFLite

ANSHUMAN87 commented on pull request #5510: URL: https://github.com/apache/incubator-tvm/pull/5510#issuecomment-625137001 Gentle ping @FrozenGene ! This is an automated message from the Apache Git Service. To respond to the

[GitHub] [incubator-tvm] FrozenGene commented on pull request #5485: [TOPI][Winograd] Optimization of Conv2d Winograd algorithm on Tensor …

FrozenGene commented on pull request #5485: URL: https://github.com/apache/incubator-tvm/pull/5485#issuecomment-625176840 > @FrozenGene > We made the following tests to go through all the layouts, > > Layout_1(the same in this PR) > input_tile = (P, CI, alpha, alpha) >

[incubator-tvm] branch master updated: [TOPI][Winograd] Optimization of Conv2d Winograd algorithm on Tensor Core (#5485)

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 e40b8bc [TOPI][Winograd] Optimization

[GitHub] [incubator-tvm] FrozenGene commented on pull request #5485: [TOPI][Winograd] Optimization of Conv2d Winograd algorithm on Tensor …

FrozenGene commented on pull request #5485: URL: https://github.com/apache/incubator-tvm/pull/5485#issuecomment-625178019 Thanks @wsl-inspur @Hzfengsy ! This is an automated message from the Apache Git Service. To respond to

[GitHub] [incubator-tvm] kazum commented on a change in pull request #5506: [WEB][RUNTIME] TVM WebAssembly JS Runtime

kazum commented on a change in pull request #5506: URL: https://github.com/apache/incubator-tvm/pull/5506#discussion_r421347977 ## File path: web/src/rpc_server.ts ## @@ -0,0 +1,379 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor

[GitHub] [incubator-tvm] dhruvaray commented on a change in pull request #5508: [TFLITE]GATHER_ND

dhruvaray commented on a change in pull request #5508: URL: https://github.com/apache/incubator-tvm/pull/5508#discussion_r421369652 ## File path: tests/python/frontend/tflite/test_forward.py ## @@ -343,6 +343,36 @@ def test_forward_gather(): _test_gather((1, 3, 3),

[GitHub] [incubator-tvm] kazum commented on a change in pull request #5506: [WEB][RUNTIME] TVM WebAssembly JS Runtime

kazum commented on a change in pull request #5506: URL: https://github.com/apache/incubator-tvm/pull/5506#discussion_r421331174 ## File path: python/tvm/contrib/emcc.py ## @@ -44,25 +42,25 @@ def create_js(output, The compile string. """ cmd = [cc] -cmd

[incubator-tvm] branch master updated: [FRONTEND][TFLite] Fully connected op conversion made in sync with TFLite (#5510)

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 b3730e5 [FRONTEND][TFLite] Fully

[GitHub] [incubator-tvm] FrozenGene commented on pull request #5510: [FRONTEND][TFLite] Fully connected op conversion made in sync with TFLite

FrozenGene commented on pull request #5510: URL: https://github.com/apache/incubator-tvm/pull/5510#issuecomment-625173020 Thanks @ANSHUMAN87 @u99127 This is an automated message from the Apache Git Service. To respond to

[GitHub] [incubator-tvm] kparzysz-quic commented on a change in pull request #5492: [RUNTIME] Hexagon driver for offloading kernels to simulator

kparzysz-quic commented on a change in pull request #5492: URL: https://github.com/apache/incubator-tvm/pull/5492#discussion_r421517804 ## File path: src/runtime/hexagon/sim/driver/pthread.h ## @@ -0,0 +1,96 @@ +/* Review comment: The reason why this is here is to be

[GitHub] [incubator-tvm] kparzysz-quic commented on a change in pull request #5535: Changes to cpp_rpc to make it work on Android (+ Hexagon offloading)

kparzysz-quic commented on a change in pull request #5535: URL: https://github.com/apache/incubator-tvm/pull/5535#discussion_r421501402 ## File path: apps/cpp_rpc/rpc_env.cc ## @@ -67,7 +67,12 @@ namespace { namespace tvm { namespace runtime { RPCEnv::RPCEnv() { - base_ =

[GitHub] [incubator-tvm] FrozenGene commented on a change in pull request #5535: Changes to cpp_rpc to make it work on Android (+ Hexagon offloading)

FrozenGene commented on a change in pull request #5535: URL: https://github.com/apache/incubator-tvm/pull/5535#discussion_r421440050 ## File path: apps/cpp_rpc/rpc_env.cc ## @@ -67,7 +67,12 @@ namespace { namespace tvm { namespace runtime { RPCEnv::RPCEnv() { - base_ =

[GitHub] [incubator-tvm] maheshambule commented on pull request #5495: [Relay, Topi] [Frontend][TFLite, MXNet] ReverseSequence operator

maheshambule commented on pull request #5495: URL: https://github.com/apache/incubator-tvm/pull/5495#issuecomment-625193573 cc: @FrozenGene, @masahi, @yongwww This is an automated message from the Apache Git Service. To

[GitHub] [incubator-tvm] FrozenGene commented on a change in pull request #5492: [RUNTIME] Hexagon driver for offloading kernels to simulator

FrozenGene commented on a change in pull request #5492: URL: https://github.com/apache/incubator-tvm/pull/5492#discussion_r421596654 ## File path: src/runtime/hexagon/sim/driver/CMakeLists.txt ## @@ -0,0 +1,62 @@ +# Licensed to the Apache Software Foundation (ASF) under one +#

[GitHub] [incubator-tvm] FrozenGene commented on a change in pull request #5492: [RUNTIME] Hexagon driver for offloading kernels to simulator

FrozenGene commented on a change in pull request #5492: URL: https://github.com/apache/incubator-tvm/pull/5492#discussion_r421596926 ## File path: src/runtime/hexagon/sim/driver/CMakeLists.txt ## @@ -0,0 +1,62 @@ +# Licensed to the Apache Software Foundation (ASF) under one +#

[GitHub] [incubator-tvm] kparzysz-quic commented on a change in pull request #5535: Changes to cpp_rpc to make it work on Android (+ Hexagon offloading)

kparzysz-quic commented on a change in pull request #5535: URL: https://github.com/apache/incubator-tvm/pull/5535#discussion_r421622213 ## File path: apps/cpp_rpc/rpc_env.cc ## @@ -67,7 +67,12 @@ namespace { namespace tvm { namespace runtime { RPCEnv::RPCEnv() { - base_ =

[GitHub] [incubator-tvm] tqchen commented on pull request #5506: [WEB][RUNTIME] TVM WebAssembly JS Runtime

tqchen commented on pull request #5506: URL: https://github.com/apache/incubator-tvm/pull/5506#issuecomment-625309110 @kazum I have updated per your comment, please take another look This is an automated message from the

[GitHub] [incubator-tvm] FrozenGene commented on a change in pull request #5492: [RUNTIME] Hexagon driver for offloading kernels to simulator

FrozenGene commented on a change in pull request #5492: URL: https://github.com/apache/incubator-tvm/pull/5492#discussion_r421605666 ## File path: src/runtime/threading_backend.cc ## @@ -255,6 +255,17 @@ int MaxConcurrency() { max_concurrency =

[GitHub] [incubator-tvm] dhruvaray commented on pull request #5508: [TFLITE]GATHER_ND

dhruvaray commented on pull request #5508: URL: https://github.com/apache/incubator-tvm/pull/5508#issuecomment-625314354 > LGTM, one query. > If out of bound indices are there, the behavior of tflite and tvm is same? Yes... Both allow invalid indices and return garbage values...

[GitHub] [incubator-tvm] FrozenGene commented on a change in pull request #5492: [RUNTIME] Hexagon driver for offloading kernels to simulator

FrozenGene commented on a change in pull request #5492: URL: https://github.com/apache/incubator-tvm/pull/5492#discussion_r421601703 ## File path: src/runtime/hexagon/sim/driver/sim_device.cc ## @@ -0,0 +1,573 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under

[GitHub] [incubator-tvm] tqchen commented on pull request #5536: [WIP][Do NOT Merge]V0.6.0 quantization backport

tqchen commented on pull request #5536: URL: https://github.com/apache/incubator-tvm/pull/5536#issuecomment-625290928 For now we will only backport bugfixes, and it would be great if we can have a clear issue(of the fix) that the backport corresponds to

[GitHub] [incubator-tvm] tqchen opened a new pull request #5537: [RPC][BUGFIX][BACKPORT-0.6] Fix bug in rpc ring buffer shrink (#5516)

tqchen opened a new pull request #5537: URL: https://github.com/apache/incubator-tvm/pull/5537 This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL

[incubator-tvm] branch v0.6 updated: [RPC][BUGFIX][BACKPORT-0.6] Fix bug in rpc ring buffer shrink (#5516) (#5537)

This is an automated email from the ASF dual-hosted git repository. tqchen pushed a commit to branch v0.6 in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git The following commit(s) were added to refs/heads/v0.6 by this push: new 802e564 [RPC][BUGFIX][BACKPORT-0.6] Fix bug

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #5506: [WEB][RUNTIME] TVM WebAssembly JS Runtime

tqchen commented on a change in pull request #5506: URL: https://github.com/apache/incubator-tvm/pull/5506#discussion_r421571419 ## File path: web/README.md ## @@ -15,163 +15,70 @@ -# TVM WebAssembly and Javascript Backend +# TVM WebAssembly Runtime -This folder

[GitHub] [incubator-tvm] kparzysz-quic commented on a change in pull request #5492: [RUNTIME] Hexagon driver for offloading kernels to simulator

kparzysz-quic commented on a change in pull request #5492: URL: https://github.com/apache/incubator-tvm/pull/5492#discussion_r421599822 ## File path: src/runtime/hexagon/sim/driver/CMakeLists.txt ## @@ -0,0 +1,62 @@ +# Licensed to the Apache Software Foundation (ASF) under one

[GitHub] [incubator-tvm] kparzysz-quic commented on a change in pull request #5492: [RUNTIME] Hexagon driver for offloading kernels to simulator

kparzysz-quic commented on a change in pull request #5492: URL: https://github.com/apache/incubator-tvm/pull/5492#discussion_r421599822 ## File path: src/runtime/hexagon/sim/driver/CMakeLists.txt ## @@ -0,0 +1,62 @@ +# Licensed to the Apache Software Foundation (ASF) under one

[GitHub] [incubator-tvm] kparzysz-quic commented on a change in pull request #5492: [RUNTIME] Hexagon driver for offloading kernels to simulator

kparzysz-quic commented on a change in pull request #5492: URL: https://github.com/apache/incubator-tvm/pull/5492#discussion_r421599822 ## File path: src/runtime/hexagon/sim/driver/CMakeLists.txt ## @@ -0,0 +1,62 @@ +# Licensed to the Apache Software Foundation (ASF) under one

[GitHub] [incubator-tvm] kparzysz-quic commented on a change in pull request #5492: [RUNTIME] Hexagon driver for offloading kernels to simulator

kparzysz-quic commented on a change in pull request #5492: URL: https://github.com/apache/incubator-tvm/pull/5492#discussion_r421616268 ## File path: src/runtime/threading_backend.cc ## @@ -255,6 +255,17 @@ int MaxConcurrency() { max_concurrency =

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #5483: [TIR][Printer] text format printer considering future parsing use

tqchen commented on a change in pull request #5483: URL: https://github.com/apache/incubator-tvm/pull/5483#discussion_r421561409 ## File path: python/tvm/tir/parser.py ## @@ -0,0 +1,24 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor

[GitHub] [incubator-tvm] kparzysz-quic commented on a change in pull request #5492: [RUNTIME] Hexagon driver for offloading kernels to simulator

kparzysz-quic commented on a change in pull request #5492: URL: https://github.com/apache/incubator-tvm/pull/5492#discussion_r421540645 ## File path: src/runtime/hexagon/sim/driver/sim_device.cc ## @@ -0,0 +1,573 @@ +/* + * Licensed to the Apache Software Foundation (ASF)

[GitHub] [incubator-tvm] kparzysz-quic commented on a change in pull request #5492: [RUNTIME] Hexagon driver for offloading kernels to simulator

kparzysz-quic commented on a change in pull request #5492: URL: https://github.com/apache/incubator-tvm/pull/5492#discussion_r421539044 ## File path: src/runtime/hexagon/sim/driver/CMakeLists.txt ## @@ -0,0 +1,62 @@ +# Licensed to the Apache Software Foundation (ASF) under one

[GitHub] [incubator-tvm] kparzysz-quic commented on a change in pull request #5492: [RUNTIME] Hexagon driver for offloading kernels to simulator

kparzysz-quic commented on a change in pull request #5492: URL: https://github.com/apache/incubator-tvm/pull/5492#discussion_r421539848 ## File path: src/runtime/hexagon/sim/driver/CMakeLists.txt ## @@ -0,0 +1,62 @@ +# Licensed to the Apache Software Foundation (ASF) under one

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #5506: [WEB][RUNTIME] TVM WebAssembly JS Runtime

tqchen commented on a change in pull request #5506: URL: https://github.com/apache/incubator-tvm/pull/5506#discussion_r421558689 ## File path: python/tvm/contrib/emcc.py ## @@ -44,25 +42,25 @@ def create_js(output, The compile string. """ cmd = [cc] -cmd

[GitHub] [incubator-tvm] FrozenGene commented on a change in pull request #5535: Changes to cpp_rpc to make it work on Android (+ Hexagon offloading)

FrozenGene commented on a change in pull request #5535: URL: https://github.com/apache/incubator-tvm/pull/5535#discussion_r421612526 ## File path: apps/cpp_rpc/rpc_env.cc ## @@ -67,7 +67,12 @@ namespace { namespace tvm { namespace runtime { RPCEnv::RPCEnv() { - base_ =

[GitHub] [incubator-tvm] anijain2305 commented on pull request #5479: [Relay-TFLite] FP32 and Quantized Object Detection Model

anijain2305 commented on pull request #5479: URL: https://github.com/apache/incubator-tvm/pull/5479#issuecomment-625401862 Ping @FrozenGene :) This is an automated message from the Apache Git Service. To respond to the

[GitHub] [incubator-tvm] yongfeng-nv commented on pull request #5382: [TE] Fix MakeLoopNest for warp memory

yongfeng-nv commented on pull request #5382: URL: https://github.com/apache/incubator-tvm/pull/5382#issuecomment-625284888 > I call tvm.driver.build_module.form_irmodule directly, in order not to run the transformation passes in lower, otherwise the result will not make a difference. Then

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #5506: [WEB][RUNTIME] TVM WebAssembly JS Runtime

tqchen commented on a change in pull request #5506: URL: https://github.com/apache/incubator-tvm/pull/5506#discussion_r421560025 ## File path: web/src/rpc_server.ts ## @@ -0,0 +1,379 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #5506: [WEB][RUNTIME] TVM WebAssembly JS Runtime

tqchen commented on a change in pull request #5506: URL: https://github.com/apache/incubator-tvm/pull/5506#discussion_r421559230 ## File path: web/Makefile ## @@ -0,0 +1,51 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license

[incubator-tvm] branch master updated (f05b911 -> c238a86)

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 f05b911 Cache PrimExpr instead of raw pointers in bound analyzer (#5533) add c238a86 fix a few bugs

[incubator-tvm] branch master updated (c238a86 -> 54d47cc)

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 c238a86 fix a few bugs with shape inference and types in the onnx importer (#5534) add 54d47cc

[GitHub] [incubator-tvm] mbrookhart opened a new pull request #5539: Add Onnx Pad v11

mbrookhart opened a new pull request #5539: URL: https://github.com/apache/incubator-tvm/pull/5539 @masahi Another ONNX op. Thanks! This is an automated message from the Apache Git Service. To respond to the message, please

[GitHub] [incubator-tvm] tqchen commented on pull request #5507: [CRT]fix to reduce RAM size during loading model

tqchen commented on pull request #5507: URL: https://github.com/apache/incubator-tvm/pull/5507#issuecomment-625459772 @siju-samuel do you mind elaborate? I still do not see why do we need to specify bits here. Is it because your pool contains a lot of single element data? Since it is

[GitHub] [incubator-tvm] siju-samuel commented on pull request #5507: [CRT]fix to reduce RAM size during loading model

siju-samuel commented on pull request #5507: URL: https://github.com/apache/incubator-tvm/pull/5507#issuecomment-625525365 @tqchen I work in a device with very limited ram availability. Actually even a few kbs is crucial for me. Im using a quantized model and the pool is 80% unit8

[GitHub] [incubator-tvm] siju-samuel edited a comment on pull request #5507: [CRT]fix to reduce RAM size during loading model

siju-samuel edited a comment on pull request #5507: URL: https://github.com/apache/incubator-tvm/pull/5507#issuecomment-625525365 @tqchen. Thanks for the review. I work in a device with very limited ram availability. Actually even a few kbs is crucial for me. Im using a quantized

[GitHub] [incubator-tvm] tqchen commented on pull request #5533: Cache PrimExpr instead of raw pointers in bound analyzer

tqchen commented on pull request #5533: URL: https://github.com/apache/incubator-tvm/pull/5533#issuecomment-625418250 cc @hzfan This is an automated message from the Apache Git Service. To respond to the message, please log

[incubator-tvm] branch master updated (e40b8bc -> f05b911)

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 e40b8bc [TOPI][Winograd] Optimization of Conv2d Winograd algorithm on Tensor Core (#5485) add f05b911

[incubator-tvm] branch master updated (b4ee81d -> 19f322d)

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 b4ee81d [RPC][BUGFIX] Fix remote device sync (#5538) add 19f322d [Refactor][std::string --> String]

[GitHub] [incubator-tvm] anijain2305 commented on pull request #5533: Cache PrimExpr instead of raw pointers in bound analyzer

anijain2305 commented on pull request #5533: URL: https://github.com/apache/incubator-tvm/pull/5533#issuecomment-625411392 Thanks @kparzysz-quic I saw the same error in https://github.com/apache/incubator-tvm/issues/5455 And I was wondering same if the objects are deallocated and

[GitHub] [incubator-tvm] tqchen commented on pull request #5447: [TOPI,RELAY][TFLITE] Sparse to dense operator

tqchen commented on pull request #5447: URL: https://github.com/apache/incubator-tvm/pull/5447#issuecomment-625469092 @dhruvaray please followup This is an automated message from the Apache Git Service. To respond to the

[incubator-tvm] branch master updated (54d47cc -> 702fd0f)

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 54d47cc [Frontend][TFLite] ADD_N operator (#5474) add 702fd0f [WEB][RUNTIME] TVM WebAssembly JS

[GitHub] [incubator-tvm] tqchen commented on pull request #5498: [Optimization] Warp level reduction support for CUDA

tqchen commented on pull request #5498: URL: https://github.com/apache/incubator-tvm/pull/5498#issuecomment-625468159 @roastduck @Hzfengsy please https://tvm.apache.org/docs/contribute/code_review.html#approve-and-request-changes-explicitly

[GitHub] [incubator-tvm] tqchen opened a new pull request #5538: [RPC][BUGFIX] Fix remote device sync

tqchen opened a new pull request #5538: URL: https://github.com/apache/incubator-tvm/pull/5538 cc @tmoreau89 @areusch This is an automated message from the Apache Git Service. To respond to the message, please log on to

[incubator-tvm] branch master updated (702fd0f -> e29e222)

This is an automated email from the ASF dual-hosted git repository. masahi pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from 702fd0f [WEB][RUNTIME] TVM WebAssembly JS Runtime (#5506) add e29e222 [RELAY][ONNX]ReduceLogSumExp

[GitHub] [incubator-tvm] masahi commented on pull request #5453: [RELAY][ONNX]ReduceLogSumExp Operator support

masahi commented on pull request #5453: URL: https://github.com/apache/incubator-tvm/pull/5453#issuecomment-625490403 Thanks @siju-samuel This is an automated message from the Apache Git Service. To respond to the message,

[incubator-tvm] branch master updated (e29e222 -> b4ee81d)

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 e29e222 [RELAY][ONNX]ReduceLogSumExp Operator support (#5453) add b4ee81d [RPC][BUGFIX] Fix remote

[GitHub] [incubator-tvm] anijain2305 edited a comment on pull request #5533: Cache PrimExpr instead of raw pointers in bound analyzer

anijain2305 edited a comment on pull request #5533: URL: https://github.com/apache/incubator-tvm/pull/5533#issuecomment-625411392 Thanks @kparzysz-quic I saw the same error in https://github.com/apache/incubator-tvm/issues/5455 And I was wondering same if the objects are

[GitHub] [incubator-tvm] siju-samuel edited a comment on pull request #5507: [CRT]fix to reduce RAM size during loading model

siju-samuel edited a comment on pull request #5507: URL: https://github.com/apache/incubator-tvm/pull/5507#issuecomment-625525365 @tqchen. Thanks for the review. I work in a device with very limited ram availability. Actually even a few kbs is crucial for me. Im using a quantized

[GitHub] [incubator-tvm] liangfu commented on issue #5060: [uTVM][Runtime] Deprecate uTVM Standalone Runtime

liangfu commented on issue #5060: URL: https://github.com/apache/incubator-tvm/issues/5060#issuecomment-625559759 Hi @Robeast, thanks for your attention. I only have a draft version of the new allocator for now, I'd like to send a PR soon this week.

[GitHub] [incubator-tvm] jroesch commented on pull request #5526: [Rust] Add first stage of updating and rewriting Rust bindings.

jroesch commented on pull request #5526: URL: https://github.com/apache/incubator-tvm/pull/5526#issuecomment-625570759 @nhynes @tqchen @ehsanmok can someone approve the changes so we can land this? it should be good to go, if you have future follow up work I'm happy to do on another

[GitHub] [incubator-tvm] roastduck commented on pull request #5382: [TE] Fix MakeLoopNest for warp memory

roastduck commented on pull request #5382: URL: https://github.com/apache/incubator-tvm/pull/5382#issuecomment-625574365 @yongfeng-nv Fixed. This is an automated message from the Apache Git Service. To respond to the

[incubator-tvm] branch master updated (19f322d -> 2b02d56)

This is an automated email from the ASF dual-hosted git repository. zhic pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from 19f322d [Refactor][std::string --> String] IRModule is updated with String (#5523) add 2b02d56

[GitHub] [incubator-tvm] siju-samuel commented on a change in pull request #5329: [Frontend][TFLite] Add parser support for shape and range

siju-samuel commented on a change in pull request #5329: URL: https://github.com/apache/incubator-tvm/pull/5329#discussion_r421938105 ## File path: python/tvm/relay/frontend/tflite.py ## @@ -579,6 +582,63 @@ def convert_tanh(self, op): return out +def

[GitHub] [incubator-tvm] tqchen opened a new pull request #5540: [RUNTIME] Store nullptr PackedFunc as nullptr for better error propagation

tqchen opened a new pull request #5540: URL: https://github.com/apache/incubator-tvm/pull/5540 cc @jroesch @ZihengJiang @zhiics This is an automated message from the Apache Git Service. To respond to the message, please log

[GitHub] [incubator-tvm] jroesch commented on a change in pull request #5527: [Rust] Second stage of Rust Refactor

jroesch commented on a change in pull request #5527: URL: https://github.com/apache/incubator-tvm/pull/5527#discussion_r421878884 ## File path: rust/tvm-rt/README.md ## @@ -0,0 +1,235 @@ + + + + + + + + + + + + + + + + + +# TVM Runtime Frontend Support + +This crate provides

[GitHub] [incubator-tvm] roastduck commented on a change in pull request #5498: [Optimization] Warp level reduction support for CUDA

roastduck commented on a change in pull request #5498: URL: https://github.com/apache/incubator-tvm/pull/5498#discussion_r421898436 ## File path: src/tir/transforms/lower_thread_allreduce.cc ## @@ -181,52 +189,196 @@ class ThreadAllreduceBuilder final : public StmtExprMutator

[GitHub] [incubator-tvm] robo-corg commented on a change in pull request #5526: [Rust] Add first stage of updating and rewriting Rust bindings.

robo-corg commented on a change in pull request #5526: URL: https://github.com/apache/incubator-tvm/pull/5526#discussion_r421879862 ## File path: rust/frontend/src/context.rs ## @@ -58,23 +58,23 @@ use crate::{function, TVMArgValue}; /// ## Example /// /// ``` -/// use

[GitHub] [incubator-tvm] dhruvaray commented on pull request #5447: [TOPI,RELAY][TFLITE] Sparse to dense operator

dhruvaray commented on pull request #5447: URL: https://github.com/apache/incubator-tvm/pull/5447#issuecomment-625629320 @siju-samuel, @u99127 - Please confirm if you are ok with the changes so that this can be merged...

[GitHub] [incubator-tvm] dhruvaray commented on pull request #5329: [Frontend][TFLite] Add parser support for shape and range

dhruvaray commented on pull request #5329: URL: https://github.com/apache/incubator-tvm/pull/5329#issuecomment-625629472 @siju-samuel - Please confirm if you are ok with the changes so that this can be merged... This is an

[GitHub] [incubator-tvm] jroesch commented on a change in pull request #5526: [Rust] Add first stage of updating and rewriting Rust bindings.

jroesch commented on a change in pull request #5526: URL: https://github.com/apache/incubator-tvm/pull/5526#discussion_r421868405 ## File path: rust/tvm-sys/src/context.rs ## @@ -0,0 +1,293 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more

[GitHub] [incubator-tvm] jroesch commented on a change in pull request #5526: [Rust] Add first stage of updating and rewriting Rust bindings.

jroesch commented on a change in pull request #5526: URL: https://github.com/apache/incubator-tvm/pull/5526#discussion_r421868908 ## File path: rust/tvm-sys/src/value.rs ## @@ -0,0 +1,95 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more

[GitHub] [incubator-tvm] wpan11nv commented on a change in pull request #5498: [Optimization] Warp level reduction support for CUDA

wpan11nv commented on a change in pull request #5498: URL: https://github.com/apache/incubator-tvm/pull/5498#discussion_r421899923 ## File path: src/tir/transforms/lower_thread_allreduce.cc ## @@ -181,52 +189,196 @@ class ThreadAllreduceBuilder final : public StmtExprMutator

[GitHub] [incubator-tvm] dhruvaray commented on pull request #5488: [TFLITE] SELECT

dhruvaray commented on pull request #5488: URL: https://github.com/apache/incubator-tvm/pull/5488#issuecomment-625629617 Ok... we can close this then... This is an automated message from the Apache Git Service. To respond to

[GitHub] [incubator-tvm] tqchen commented on pull request #5507: [CRT]fix to reduce RAM size during loading model

tqchen commented on pull request #5507: URL: https://github.com/apache/incubator-tvm/pull/5507#issuecomment-625527871 shouldn't the `size` argument in the pool already is reflected number of bytes(thus taking the data type into consideration?)

[GitHub] [incubator-tvm] adelbertc commented on a change in pull request #5526: [Rust] Add first stage of updating and rewriting Rust bindings.

adelbertc commented on a change in pull request #5526: URL: https://github.com/apache/incubator-tvm/pull/5526#discussion_r421878601 ## File path: rust/tvm-sys/build.rs ## @@ -0,0 +1,117 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more

[GitHub] [incubator-tvm] wpan11nv commented on a change in pull request #5498: [Optimization] Warp level reduction support for CUDA

wpan11nv commented on a change in pull request #5498: URL: https://github.com/apache/incubator-tvm/pull/5498#discussion_r421901493 ## File path: src/tir/transforms/lower_thread_allreduce.cc ## @@ -330,6 +482,59 @@ class ThreadAllreduceBuilder final : public StmtExprMutator {

[GitHub] [incubator-tvm] spectrometerHBH commented on a change in pull request #5483: [TIR][Printer] text format printer considering future parsing use

spectrometerHBH commented on a change in pull request #5483: URL: https://github.com/apache/incubator-tvm/pull/5483#discussion_r421901168 ## File path: python/tvm/tir/parser.py ## @@ -0,0 +1,24 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [incubator-tvm] FrozenGene commented on pull request #5535: Changes to cpp_rpc to make it work on Android (+ Hexagon offloading)

FrozenGene commented on pull request #5535: URL: https://github.com/apache/incubator-tvm/pull/5535#issuecomment-625612254 THANKS @kparzysz-quic This is an automated message from the Apache Git Service. To respond to the

[incubator-tvm] branch master updated: Changes to cpp_rpc to make it work on Android (+ Hexagon offloading) (#5535)

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 1b17b73 Changes to cpp_rpc to make it

[GitHub] [incubator-tvm] liangfu commented on a change in pull request #5492: [RUNTIME] Hexagon driver for offloading kernels to simulator

liangfu commented on a change in pull request #5492: URL: https://github.com/apache/incubator-tvm/pull/5492#discussion_r421883580 ## File path: src/runtime/hexagon/sim/driver/CMakeLists.txt ## @@ -0,0 +1,62 @@ +# Licensed to the Apache Software Foundation (ASF) under one

[GitHub] [incubator-tvm] roastduck commented on a change in pull request #5498: [Optimization] Warp level reduction support for CUDA

roastduck commented on a change in pull request #5498: URL: https://github.com/apache/incubator-tvm/pull/5498#discussion_r421883868 ## File path: src/tir/transforms/lower_thread_allreduce.cc ## @@ -119,19 +126,20 @@ class ThreadAllreduceBuilder final : public StmtExprMutator

[GitHub] [incubator-tvm] tmoreau89 opened a new pull request #5541: [DOCS] Fix bad restructured text formatting for VTA install guide

tmoreau89 opened a new pull request #5541: URL: https://github.com/apache/incubator-tvm/pull/5541 Formatting is broken in VTA docs due to transition from markdown to restructured text. The doc was re-formatted and tested in a sphinx preview app (https://livesphinx.herokuapp.com/) in order

[incubator-tvm] branch master updated (2b02d56 -> 786dfb6)

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 2b02d56 [RUNTIME] Store nullptr PackedFunc as nullptr for better error propagation (#5540) add 786dfb6

[GitHub] [incubator-tvm] FrozenGene commented on pull request #5479: [Relay-TFLite] FP32 and Quantized Object Detection Model

FrozenGene commented on pull request #5479: URL: https://github.com/apache/incubator-tvm/pull/5479#issuecomment-625607904 THANKS @anijain2305 @siju-samuel @mbaret This is an automated message from the Apache Git Service. To

[GitHub] [incubator-tvm-vta] huajsj commented on pull request #5: Add c++ and python local deploy example

huajsj commented on pull request #5: URL: https://github.com/apache/incubator-tvm-vta/pull/5#issuecomment-625568864 @tmoreau89 , could you help to review this patch again? Thanks Regards Hua This is an automated

[GitHub] [incubator-tvm] jroesch commented on pull request #5526: [Rust] Add first stage of updating and rewriting Rust bindings.

jroesch commented on pull request #5526: URL: https://github.com/apache/incubator-tvm/pull/5526#issuecomment-625568446 I addressed all the feedback except a few things that don't work like changing to `get_mut_ptr()` which doesn't work due to the array being borrowed and not mutably

[GitHub] [incubator-tvm] adelbertc commented on a change in pull request #5526: [Rust] Add first stage of updating and rewriting Rust bindings.

adelbertc commented on a change in pull request #5526: URL: https://github.com/apache/incubator-tvm/pull/5526#discussion_r421879244 ## File path: rust/tvm-sys/src/context.rs ## @@ -0,0 +1,285 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more

[GitHub] [incubator-tvm] siju-samuel commented on pull request #5507: [CRT]fix to reduce RAM size during loading model

siju-samuel commented on pull request #5507: URL: https://github.com/apache/incubator-tvm/pull/5507#issuecomment-625537719 @tqchen Ideally yes. There may be some calcuation issue. I will verify once again in case of crt what is happening and get back.

[GitHub] [incubator-tvm] roastduck commented on a change in pull request #5498: [Optimization] Warp level reduction support for CUDA

roastduck commented on a change in pull request #5498: URL: https://github.com/apache/incubator-tvm/pull/5498#discussion_r421887613 ## File path: src/tir/transforms/lower_thread_allreduce.cc ## @@ -330,6 +482,59 @@ class ThreadAllreduceBuilder final : public StmtExprMutator {

[GitHub] [incubator-tvm] spectrometerHBH commented on a change in pull request #5483: [TIR][Printer] text format printer considering future parsing use

spectrometerHBH commented on a change in pull request #5483: URL: https://github.com/apache/incubator-tvm/pull/5483#discussion_r421900677 ## File path: python/tvm/tir/parser.py ## @@ -0,0 +1,24 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

  1   2   >