[GitHub] [incubator-tvm] FrozenGene commented on pull request #6117: Use auto-tuner to improve conv2d_gemm performance

FrozenGene commented on pull request #6117: URL: https://github.com/apache/incubator-tvm/pull/6117#issuecomment-680688614 Thanks @giuseros @anijain2305 It is merged now. This is an automated message from the Apache Git Servic

[GitHub] [incubator-tvm] FrozenGene merged pull request #6117: Use auto-tuner to improve conv2d_gemm performance

FrozenGene merged pull request #6117: URL: https://github.com/apache/incubator-tvm/pull/6117 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 (883a28d -> 617949d)

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 883a28d save (#6338) add 617949d Use auto-tuner to improve conv2d_gemm performance (#6117) No new revi

[GitHub] [incubator-tvm] FrozenGene commented on a change in pull request #6117: Use auto-tuner to improve conv2d_gemm performance

FrozenGene commented on a change in pull request #6117: URL: https://github.com/apache/incubator-tvm/pull/6117#discussion_r477065824 ## File path: python/tvm/topi/arm_cpu/tensor_intrin.py ## @@ -21,7 +21,186 @@ from tvm import te from tvm.contrib import util, clang -def gem

[GitHub] [incubator-tvm] MarisaKirisame commented on a change in pull request #6336: [Relay][Training] Make AutoDiff thread through global function.

MarisaKirisame commented on a change in pull request #6336: URL: https://github.com/apache/incubator-tvm/pull/6336#discussion_r477064941 ## File path: src/relay/transforms/gradient.cc ## @@ -438,12 +449,17 @@ Expr BPEmpty() { struct ReverseAD : ExprMutator { using ADVarMa

[GitHub] [incubator-tvm] MarisaKirisame commented on a change in pull request #6336: [Relay][Training] Make AutoDiff thread through global function.

MarisaKirisame commented on a change in pull request #6336: URL: https://github.com/apache/incubator-tvm/pull/6336#discussion_r477065065 ## File path: src/relay/transforms/gradient.cc ## @@ -518,22 +533,29 @@ struct ReverseAD : ExprMutator { orig_var->checked_type_ = c

[GitHub] [incubator-tvm] FrozenGene commented on a change in pull request #6117: Use auto-tuner to improve conv2d_gemm performance

FrozenGene commented on a change in pull request #6117: URL: https://github.com/apache/incubator-tvm/pull/6117#discussion_r477064579 ## File path: python/tvm/topi/arm_cpu/tensor_intrin.py ## @@ -21,7 +21,186 @@ from tvm import te from tvm.contrib import util, clang -def gem

[GitHub] [incubator-tvm] FrozenGene commented on a change in pull request #6137: Better grouped convolution for CPU targets

FrozenGene commented on a change in pull request #6137: URL: https://github.com/apache/incubator-tvm/pull/6137#discussion_r477060409 ## File path: topi/python/topi/arm_cpu/group_conv2d.py ## @@ -0,0 +1,310 @@ +import tvm +from tvm import autotvm +from tvm import te +from ..util

[GitHub] [incubator-tvm] FrozenGene commented on a change in pull request #6341: [Easy fix] Make able to compile with msvc, clang

FrozenGene commented on a change in pull request #6341: URL: https://github.com/apache/incubator-tvm/pull/6341#discussion_r477058076 ## File path: src/target/llvm/codegen_hexagon.cc ## @@ -636,7 +636,10 @@ bool UsesExportABI(const PrimFunc& f) { return false; } -__attribu

[GitHub] [incubator-tvm] FrozenGene commented on pull request #6206: [Caffe Frontend] introduce caffe frontend for tvm

FrozenGene commented on pull request #6206: URL: https://github.com/apache/incubator-tvm/pull/6206#issuecomment-680679172 > ```python > from tvm.relay.frontend import caffe_pb2 as pb > ``` where is from `tvm.relay.frontend import caffe_pb2 as pb`, i don't see it in this pr. And

[GitHub] [incubator-tvm] FrozenGene commented on a change in pull request #6206: [Caffe Frontend] introduce caffe frontend for tvm

FrozenGene commented on a change in pull request #6206: URL: https://github.com/apache/incubator-tvm/pull/6206#discussion_r477054028 ## File path: tests/python/frontend/caffe/test_forward.py ## @@ -0,0 +1,1003 @@ +# Licensed to the Apache Software Foundation (ASF) under one +#

[GitHub] [incubator-tvm] yukatayu opened a new pull request #6341: [Easy fix] Make able to compile with msvc, clang

yukatayu opened a new pull request #6341: URL: https://github.com/apache/incubator-tvm/pull/6341 HEAD ( 1a26a2e9e073e7fb579390edba8baf826743909c ) cannot be compiled with msvc. So, I added some `#include` and `#ifdef` to make it compilable. ---

[GitHub] [incubator-tvm] wweic commented on a change in pull request #5881: [Relay] Mutual Recursion Support

wweic commented on a change in pull request #5881: URL: https://github.com/apache/incubator-tvm/pull/5881#discussion_r475262844 ## File path: python/tvm/ir/module.py ## @@ -87,6 +87,10 @@ def _add(self, var, val, update=False): var = _ty.GlobalTypeVar(var)

[GitHub] [incubator-tvm] jroesch commented on a change in pull request #6274: [Diagnostics][Relay][InferType] Refactor InferType to work on whole module, and use new diagnostics.

jroesch commented on a change in pull request #6274: URL: https://github.com/apache/incubator-tvm/pull/6274#discussion_r477047300 ## File path: src/relay/transforms/type_infer.cc ## @@ -98,11 +100,11 @@ class TypeInferencer : private ExprFunctor, public: // constructors

[GitHub] [incubator-tvm] fernchen commented on pull request #6206: [Caffe Frontend] introduce caffe frontend for tvm

fernchen commented on pull request #6206: URL: https://github.com/apache/incubator-tvm/pull/6206#issuecomment-680668291 > @fernchen please try to send another dummy commit to retrigger the CI, @FrozenGene please followup. I think we can merge once all the tests are resolved @tqchen

[GitHub] [incubator-tvm] ashutoshparkhi opened a new issue #6340: Faster RCNN: Unable to compile for CPU because topk fails with unsupported number of arguments

ashutoshparkhi opened a new issue #6340: URL: https://github.com/apache/incubator-tvm/issues/6340 Hello, This the variant that fails with topk error. http://download.tensorflow.org/models/object_detection/faster_rcnn_inception_v2_coco_2018_01_28.tar.gz Error: **%

[GitHub] [incubator-tvm] jroesch commented on a change in pull request #6336: [Relay][Training] Make AutoDiff thread through global function.

jroesch commented on a change in pull request #6336: URL: https://github.com/apache/incubator-tvm/pull/6336#discussion_r477033674 ## File path: src/relay/transforms/gradient.cc ## @@ -518,22 +533,29 @@ struct ReverseAD : ExprMutator { orig_var->checked_type_ = call->ch

[GitHub] [incubator-tvm] jroesch commented on a change in pull request #6336: [Relay][Training] Make AutoDiff thread through global function.

jroesch commented on a change in pull request #6336: URL: https://github.com/apache/incubator-tvm/pull/6336#discussion_r477033513 ## File path: src/relay/transforms/gradient.cc ## @@ -438,12 +449,17 @@ Expr BPEmpty() { struct ReverseAD : ExprMutator { using ADVarMap = std

[GitHub] [incubator-tvm] jroesch commented on a change in pull request #6336: [Relay][Training] Make AutoDiff thread through global function.

jroesch commented on a change in pull request #6336: URL: https://github.com/apache/incubator-tvm/pull/6336#discussion_r477033578 ## File path: src/relay/transforms/gradient.cc ## @@ -438,12 +449,17 @@ Expr BPEmpty() { struct ReverseAD : ExprMutator { using ADVarMap = std

[GitHub] [incubator-tvm] jroesch commented on a change in pull request #6336: [Relay][Training] Make AutoDiff thread through global function.

jroesch commented on a change in pull request #6336: URL: https://github.com/apache/incubator-tvm/pull/6336#discussion_r477033326 ## File path: src/relay/transforms/gradient.cc ## @@ -85,7 +85,7 @@ Expr DeGlobal(const Optional& mod, const Expr& e) { if (mod.defined() && x) {

[GitHub] [incubator-tvm] tmoreau89 commented on pull request #6126: [VTA][OpenCL] intelfocl

tmoreau89 commented on pull request #6126: URL: https://github.com/apache/incubator-tvm/pull/6126#issuecomment-680580847 @liangfu would you mind doing a pass on this PR as well? This is an automated message from the Apache Gi

[GitHub] [incubator-tvm] tmoreau89 commented on pull request #6126: [VTA][OpenCL] intelfocl

tmoreau89 commented on pull request #6126: URL: https://github.com/apache/incubator-tvm/pull/6126#issuecomment-680579495 Thanks overall the PR is in good shape. I think that we'll need to merge the incubator-tvm-vta PR first, before we merge this one in (due to the bump on the VTA submodul

[GitHub] [incubator-tvm] tmoreau89 commented on a change in pull request #6126: [VTA][OpenCL] intelfocl

tmoreau89 commented on a change in pull request #6126: URL: https://github.com/apache/incubator-tvm/pull/6126#discussion_r477025169 ## File path: vta/runtime/runtime.cc ## @@ -429,14 +542,24 @@ class UopQueue : public BaseQueue { buff_size += cache_[i]->size() * kElemByt

[GitHub] [incubator-tvm] tmoreau89 commented on a change in pull request #6126: [VTA][OpenCL] intelfocl

tmoreau89 commented on a change in pull request #6126: URL: https://github.com/apache/incubator-tvm/pull/6126#discussion_r477024974 ## File path: vta/runtime/runtime.cc ## @@ -329,7 +442,7 @@ class BaseQueue { // End location of current SRAM write in FIFO mode uint32_t sr

[GitHub] [incubator-tvm] tmoreau89 commented on a change in pull request #6126: [VTA][OpenCL] intelfocl

tmoreau89 commented on a change in pull request #6126: URL: https://github.com/apache/incubator-tvm/pull/6126#discussion_r477024332 ## File path: src/tir/transforms/lower_tvm_builtin.cc ## @@ -88,16 +88,6 @@ class BuiltinLower : public StmtExprMutator { op = stmt.as();

[GitHub] [incubator-tvm] tmoreau89 commented on a change in pull request #6126: [VTA][OpenCL] intelfocl

tmoreau89 commented on a change in pull request #6126: URL: https://github.com/apache/incubator-tvm/pull/6126#discussion_r477022969 ## File path: python/tvm/autotvm/task/topi_integration.py ## @@ -227,17 +227,21 @@ def wrapper(outs, *args, **kwargs): return _decorate -

[GitHub] [incubator-tvm-vta] vegaluisjose opened a new pull request #10: Fixes for supporting Vivado 2020.1

vegaluisjose opened a new pull request #10: URL: https://github.com/apache/incubator-tvm-vta/pull/10 @tmoreau89 This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and

[GitHub] [incubator-tvm-vta] tmoreau89 commented on pull request #9: [Hardware][OpenCL] Intelfocl support

tmoreau89 commented on pull request #9: URL: https://github.com/apache/incubator-tvm-vta/pull/9#issuecomment-680545019 I've made other minor request, but overall the PR is shaping up well. We can stick to `intelfocl` as a target name. For documentation's stake, can you add a README file un

[GitHub] [incubator-tvm-vta] tmoreau89 commented on a change in pull request #9: [Hardware][OpenCL] Intelfocl support

tmoreau89 commented on a change in pull request #9: URL: https://github.com/apache/incubator-tvm-vta/pull/9#discussion_r477016190 ## File path: config/vta_cost.py ## @@ -0,0 +1,102 @@ +# cost function for intelfocl 32*32 gemm version +def cal_cost(insn): +""" +Cal the r

[GitHub] [incubator-tvm-vta] tmoreau89 commented on a change in pull request #9: [Hardware][OpenCL] Intelfocl support

tmoreau89 commented on a change in pull request #9: URL: https://github.com/apache/incubator-tvm-vta/pull/9#discussion_r477015151 ## File path: src/sim/sim_driver.cc ## @@ -181,6 +181,51 @@ class SRAM { } memset(sram_ptr, 0, kElemBytes * xtotal * op->y_pad_1); } +

[incubator-tvm] branch master updated (1a26a2e -> 883a28d)

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 1a26a2e [Relay] Make check stricter by using Feature. Fixed multiple bugs. (#6326) add 883a28d save (#63

[GitHub] [incubator-tvm-vta] tmoreau89 commented on a change in pull request #9: [Hardware][OpenCL] Intelfocl support

tmoreau89 commented on a change in pull request #9: URL: https://github.com/apache/incubator-tvm-vta/pull/9#discussion_r477014763 ## File path: src/oclfpga/oclfpga_driver.cc ## @@ -0,0 +1,94 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contr

[GitHub] [incubator-tvm] tmoreau89 commented on a change in pull request #6125: [VTA][OpenCL] add device_annot support in graphpack

tmoreau89 commented on a change in pull request #6125: URL: https://github.com/apache/incubator-tvm/pull/6125#discussion_r477013670 ## File path: python/tvm/relay/op/_tensor.py ## @@ -87,6 +87,10 @@ register_broadcast_schedule("fast_exp") register_broadcast_schedule("fast_tan

[GitHub] [incubator-tvm] zhiics commented on pull request #6338: [Relay] fix typo

zhiics commented on pull request #6338: URL: https://github.com/apache/incubator-tvm/pull/6338#issuecomment-680512850 Thanks @MarisaKirisame @jroesch This is an automated message from the Apache Git Service. To respond to th

[GitHub] [incubator-tvm] zhiics merged pull request #6338: [Relay] fix typo

zhiics merged pull request #6338: URL: https://github.com/apache/incubator-tvm/pull/6338 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 g

[GitHub] [incubator-tvm] tmoreau89 commented on a change in pull request #6125: [VTA][OpenCL] add device_annot support in graphpack

tmoreau89 commented on a change in pull request #6125: URL: https://github.com/apache/incubator-tvm/pull/6125#discussion_r477013567 ## File path: vta/python/vta/top/graphpack.py ## @@ -449,18 +549,46 @@ def graph_pack(expr, 'expr.astext(show_meta_data=False)'. When cou

[GitHub] [incubator-tvm] tmoreau89 commented on a change in pull request #6125: [VTA][OpenCL] add device_annot support in graphpack

tmoreau89 commented on a change in pull request #6125: URL: https://github.com/apache/incubator-tvm/pull/6125#discussion_r477013469 ## File path: vta/python/vta/top/graphpack.py ## @@ -174,6 +174,103 @@ def _operator_idx_inc(expr, count_meta, operator_current_idx): op

[GitHub] [incubator-tvm] hypercubestart commented on a change in pull request #6336: [Relay][Training] Make AutoDiff thread through global function.

hypercubestart commented on a change in pull request #6336: URL: https://github.com/apache/incubator-tvm/pull/6336#discussion_r476912921 ## File path: src/relay/transforms/gradient.cc ## @@ -85,7 +85,7 @@ Expr DeGlobal(const Optional& mod, const Expr& e) { if (mod.defined()

[GitHub] [incubator-tvm] tmoreau89 commented on pull request #6125: [VTA][OpenCL] add device_annot support in graphpack

tmoreau89 commented on pull request #6125: URL: https://github.com/apache/incubator-tvm/pull/6125#issuecomment-680508143 @zhanghaohit thanks for the ping, @ZihengJiang can you help me review this PR? This is an automated mes

[GitHub] [incubator-tvm] lsy643 commented on pull request #6108: Fix CUDA Compute Function For `get_valid_counts` and `nms`

lsy643 commented on pull request #6108: URL: https://github.com/apache/incubator-tvm/pull/6108#issuecomment-680485005 @yongwww @Laurawly Sorry for the late response, I am being quite busy at work recently. I will try to fix the error and run the benchmark by the end of this week -

[GitHub] [incubator-tvm] mwillsey opened a new pull request #6339: Improve Rust bindings: Map, Array, String, various IR nodes

mwillsey opened a new pull request #6339: URL: https://github.com/apache/incubator-tvm/pull/6339 I've been working on integrating [egg](https://github.com/mwillsey/egg) into TVM, and I've needed to add several features to the Rust bindings. With this much, it's possible to get some useful

[GitHub] [incubator-tvm] MarisaKirisame opened a new pull request #6338: [Relay] fix typo

MarisaKirisame opened a new pull request #6338: URL: https://github.com/apache/incubator-tvm/pull/6338 Thanks for contributing to TVM! Please refer to guideline https://tvm.apache.org/docs/contribute/ for useful information and tips. After the pull request is submitted, please request co

[GitHub] [incubator-tvm] comaniac commented on a change in pull request #6310: [Ansor][AutoTVM v2.0] Phase 2: Evolutionary Search

comaniac commented on a change in pull request #6310: URL: https://github.com/apache/incubator-tvm/pull/6310#discussion_r476904095 ## File path: src/auto_scheduler/search_policy/sketch_policy_rules.cc ## @@ -908,7 +795,362 @@ InitPopulationRule::ResultKind InitThreadBind::Appl

[GitHub] [incubator-tvm] MarisaKirisame commented on a change in pull request #6274: [Diagnostics][Relay][InferType] Refactor InferType to work on whole module, and use new diagnostics.

MarisaKirisame commented on a change in pull request #6274: URL: https://github.com/apache/incubator-tvm/pull/6274#discussion_r476763139 ## File path: src/ir/module.cc ## @@ -174,46 +174,28 @@ tvm::Array IRModuleNode::GetGlobalTypeVars() const { return tvm::Array(global_typ

[GitHub] [incubator-tvm] zhiics opened a new pull request #6337: [RELAY][VM] Enable heterogeneous execution to VM

zhiics opened a new pull request #6337: URL: https://github.com/apache/incubator-tvm/pull/6337 Currently, the dynamic models can only be executed for on CPU. The GPU execution is not allowed for these models because they have shape functions to do runtime type inference. These functions ma

[GitHub] [incubator-tvm] comaniac commented on a change in pull request #6310: [Ansor][AutoTVM v2.0] Phase 2: Evolutionary Search

comaniac commented on a change in pull request #6310: URL: https://github.com/apache/incubator-tvm/pull/6310#discussion_r476794305 ## File path: src/auto_scheduler/search_policy/sketch_policy_rules.cc ## @@ -908,7 +795,362 @@ InitPopulationRule::ResultKind InitThreadBind::Appl

[GitHub] [incubator-tvm] merrymercy commented on a change in pull request #6310: [Ansor][AutoTVM v2.0] Phase 2: Evolutionary Search

merrymercy commented on a change in pull request #6310: URL: https://github.com/apache/incubator-tvm/pull/6310#discussion_r476790568 ## File path: src/auto_scheduler/search_policy/sketch_policy.cc ## @@ -363,8 +376,150 @@ Array SketchPolicyNode::EvolutionarySearch(const Array&

[GitHub] [incubator-tvm] merrymercy commented on a change in pull request #6310: [Ansor][AutoTVM v2.0] Phase 2: Evolutionary Search

merrymercy commented on a change in pull request #6310: URL: https://github.com/apache/incubator-tvm/pull/6310#discussion_r476790568 ## File path: src/auto_scheduler/search_policy/sketch_policy.cc ## @@ -363,8 +376,150 @@ Array SketchPolicyNode::EvolutionarySearch(const Array&

[GitHub] [incubator-tvm] merrymercy commented on a change in pull request #6310: [Ansor][AutoTVM v2.0] Phase 2: Evolutionary Search

merrymercy commented on a change in pull request #6310: URL: https://github.com/apache/incubator-tvm/pull/6310#discussion_r476788806 ## File path: src/auto_scheduler/search_policy/sketch_policy_rules.cc ## @@ -908,7 +795,362 @@ InitPopulationRule::ResultKind InitThreadBind::Ap

[GitHub] [incubator-tvm] merrymercy commented on a change in pull request #6310: [Ansor][AutoTVM v2.0] Phase 2: Evolutionary Search

merrymercy commented on a change in pull request #6310: URL: https://github.com/apache/incubator-tvm/pull/6310#discussion_r476781710 ## File path: src/auto_scheduler/search_policy/sketch_policy.cc ## @@ -363,8 +376,150 @@ Array SketchPolicyNode::EvolutionarySearch(const Array&

[GitHub] [incubator-tvm] tqchen closed issue #6320: [Auto-TVM] How to Auto tune the model on iOS device

tqchen closed issue #6320: URL: https://github.com/apache/incubator-tvm/issues/6320 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] tqchen commented on issue #6320: [Auto-TVM] How to Auto tune the model on iOS device

tqchen commented on issue #6320: URL: https://github.com/apache/incubator-tvm/issues/6320#issuecomment-680280013 move to https://discuss.tvm.ai/t/auto-tvm-how-to-auto-tune-the-model-on-ios-device/7681/3 This is an automated

[GitHub] [incubator-tvm] tqchen closed issue #6329: Android shared lib (so) can not run on Android 4.4.2

tqchen closed issue #6329: URL: https://github.com/apache/incubator-tvm/issues/6329 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] tqchen commented on issue #6329: Android shared lib (so) can not run on Android 4.4.2

tqchen commented on issue #6329: URL: https://github.com/apache/incubator-tvm/issues/6329#issuecomment-680279563 Thanks for reporting the problem, please open a trouble shooting thread on https://discuss.tvm.ai/ Perhaps you should use the same ndk that comes with the corresponding android

[GitHub] [incubator-tvm] tqchen closed issue #6330: [WASM] Cannot find global function runtime.SystemLib

tqchen closed issue #6330: URL: https://github.com/apache/incubator-tvm/issues/6330 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] tqchen commented on issue #6330: [WASM] Cannot find global function runtime.SystemLib

tqchen commented on issue #6330: URL: https://github.com/apache/incubator-tvm/issues/6330#issuecomment-680279182 Please follow the instructions in https://github.com/apache/incubator-tvm/blob/master/tests/scripts/task_web_wasm.sh as they are tested through CI. Let us move further c

[GitHub] [incubator-tvm] MarisaKirisame commented on pull request #5881: [Relay] Mutual Recursion Support

MarisaKirisame commented on pull request #5881: URL: https://github.com/apache/incubator-tvm/pull/5881#issuecomment-680278434 @hypercubestart sorry to put this on hold, but IMHO 6274 is an essential PR and we should focus on it with stronger priority. everything is good and we will merge t

[GitHub] [incubator-tvm] jroesch commented on pull request #5881: [Relay] Mutual Recursion Support

jroesch commented on pull request #5881: URL: https://github.com/apache/incubator-tvm/pull/5881#issuecomment-680276865 Can we hold off on merging this until #6274 lands? This heavily changes the way the type inferencer works. --

[GitHub] [incubator-tvm] MarisaKirisame opened a new pull request #6336: [Relay][Training] Make AutoDiff thread through global function.

MarisaKirisame opened a new pull request #6336: URL: https://github.com/apache/incubator-tvm/pull/6336 @junrushao1994 @jroesch @vinx13 @altanh @icemelon9 @hypercubestart @t-vi can you guys help review? This is an automated m

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #6333: Add docker/lint.sh, for running dockerized lint scripts locally

zhiics commented on a change in pull request #6333: URL: https://github.com/apache/incubator-tvm/pull/6333#discussion_r476713063 ## File path: tests/python/unittest/test_filter_untracked.py ## @@ -0,0 +1,178 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or

[GitHub] [incubator-tvm] giuseros commented on pull request #6117: Use auto-tuner to improve conv2d_gemm performance

giuseros commented on pull request #6117: URL: https://github.com/apache/incubator-tvm/pull/6117#issuecomment-680226417 Hi @FrozenGene , Any update on this? Thanks again, Giuseppe This is an automated message fr

[GitHub] [incubator-tvm] areusch commented on pull request #6333: Add docker/lint.sh, for running dockerized lint scripts locally

areusch commented on pull request #6333: URL: https://github.com/apache/incubator-tvm/pull/6333#issuecomment-680222705 it looks like there are some more limitations around running `docker/bash.sh` within a git worktree. I added changes to the scripts in this PR to be compatible with worktr

[GitHub] [incubator-tvm] tqchen commented on pull request #6333: Add docker/lint.sh, for running dockerized lint scripts locally

tqchen commented on pull request #6333: URL: https://github.com/apache/incubator-tvm/pull/6333#issuecomment-680222100 also cc @zhiics @yzhliu This is an automated message from the Apache Git Service. To respond to the messag

[GitHub] [incubator-tvm] areusch commented on a change in pull request #6333: Add docker/lint.sh, for running dockerized lint scripts locally

areusch commented on a change in pull request #6333: URL: https://github.com/apache/incubator-tvm/pull/6333#discussion_r476682254 ## File path: docker/lint.sh ## @@ -0,0 +1,74 @@ +#!/bin/bash -e +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributo

[GitHub] [incubator-tvm] areusch commented on a change in pull request #6333: Add docker/lint.sh, for running dockerized lint scripts locally

areusch commented on a change in pull request #6333: URL: https://github.com/apache/incubator-tvm/pull/6333#discussion_r476681765 ## File path: tests/lint/pylint.sh ## @@ -0,0 +1,21 @@ +#!/bin/bash -e +# Licensed to the Apache Software Foundation (ASF) under one +# or more cont

[GitHub] [incubator-tvm] areusch commented on a change in pull request #6333: Add docker/lint.sh, for running dockerized lint scripts locally

areusch commented on a change in pull request #6333: URL: https://github.com/apache/incubator-tvm/pull/6333#discussion_r476681151 ## File path: tests/lint/cppdocs.sh ## @@ -0,0 +1,28 @@ +#!/bin/bash -e +# Licensed to the Apache Software Foundation (ASF) under one +# or more con

[GitHub] [incubator-tvm] areusch commented on a change in pull request #6333: Add docker/lint.sh, for running dockerized lint scripts locally

areusch commented on a change in pull request #6333: URL: https://github.com/apache/incubator-tvm/pull/6333#discussion_r476680526 ## File path: tests/lint/check_asf_header.sh ## @@ -0,0 +1,48 @@ +#!/bin/bash -e +# Licensed to the Apache Software Foundation (ASF) under one +# or

[GitHub] [incubator-tvm] jroesch commented on pull request #6289: [Relay] Enhance relay.split(), allow splitted dim to be dynamic

jroesch commented on pull request #6289: URL: https://github.com/apache/incubator-tvm/pull/6289#issuecomment-680211971 cc @mbrookhart This is an automated message from the Apache Git Service. To respond to the message, pleas

[GitHub] [incubator-tvm] jroesch merged pull request #6326: [Relay] Make check stricter by using Feature. Fixed multiple bugs.

jroesch merged pull request #6326: URL: https://github.com/apache/incubator-tvm/pull/6326 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 (751982e -> 1a26a2e)

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 751982e [FIX][VM] Fix relay vm optimize (#6322) add 1a26a2e [Relay] Make check stricter by using Featu

[GitHub] [incubator-tvm] kparzysz-quic commented on pull request #6331: [TESTS] Refactor tests to run on either the GPU or CPU

kparzysz-quic commented on pull request #6331: URL: https://github.com/apache/incubator-tvm/pull/6331#issuecomment-680181562 Currently there is no good way to switch away from `str` here, but the question is how much work would it take to allow, for example, two different 'cuda' devices to

[GitHub] [incubator-tvm] tkonolige commented on a change in pull request #6331: [TESTS] Refactor tests to run on either the GPU or CPU

tkonolige commented on a change in pull request #6331: URL: https://github.com/apache/incubator-tvm/pull/6331#discussion_r476630571 ## File path: python/tvm/testing.py ## @@ -285,4 +288,184 @@ def _check_forward(constraints1, constraints2, varmap, backvarmap):

[GitHub] [incubator-tvm] kparzysz-quic commented on a change in pull request #6331: [TESTS] Refactor tests to run on either the GPU or CPU

kparzysz-quic commented on a change in pull request #6331: URL: https://github.com/apache/incubator-tvm/pull/6331#discussion_r476629728 ## File path: python/tvm/testing.py ## @@ -285,4 +288,184 @@ def _check_forward(constraints1, constraints2, varmap, backvarmap):

[incubator-tvm-site] branch master updated: Added TVM vision statement to about page (#14)

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-site.git The following commit(s) were added to refs/heads/master by this push: new 018d5b3 Added TVM vision statement

[incubator-tvm-site] branch asf-site updated: Build at Tue Aug 25 10:45:08 PDT 2020

This is an automated email from the ASF dual-hosted git repository. tqchen pushed a commit to branch asf-site in repository https://gitbox.apache.org/repos/asf/incubator-tvm-site.git The following commit(s) were added to refs/heads/asf-site by this push: new cdde8c2 Build at Tue Aug 25 10:

[GitHub] [incubator-tvm] ANSHUMAN87 commented on pull request #6238: [TIR][Transform]Block scope hoisting added

ANSHUMAN87 commented on pull request #6238: URL: https://github.com/apache/incubator-tvm/pull/6238#issuecomment-680171849 @MarisaKirisame : CI is fixed now! Would you please provide your valuable opinion on this [section](https://github.com/apache/incubator-tvm/pull/6238#discussion_r476244

[GitHub] [incubator-tvm] tkonolige commented on a change in pull request #6331: [TESTS] Refactor tests to run on either the GPU or CPU

tkonolige commented on a change in pull request #6331: URL: https://github.com/apache/incubator-tvm/pull/6331#discussion_r476625453 ## File path: python/tvm/testing.py ## @@ -285,4 +288,184 @@ def _check_forward(constraints1, constraints2, varmap, backvarmap):

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #6331: [TESTS] Refactor tests to run on either the GPU or CPU

tqchen commented on a change in pull request #6331: URL: https://github.com/apache/incubator-tvm/pull/6331#discussion_r476625703 ## File path: tests/scripts/setup-pytest-env.sh ## @@ -26,5 +26,20 @@ else fi set -u +export TVM_TEST_DEVICES="" +while test $# -gt 0 +do +ca

[GitHub] [incubator-tvm] tkonolige commented on pull request #6331: [TESTS] Refactor tests to run on either the GPU or CPU

tkonolige commented on pull request #6331: URL: https://github.com/apache/incubator-tvm/pull/6331#issuecomment-680169507 @kparzysz-quic I agree that using strings for targets here is pretty awkward. Is there a better way to check which device a target requires? I see that #6315 makes targe

[GitHub] [incubator-tvm] comaniac commented on a change in pull request #6302: [tvmc] command line driver 'compile' (part 2/4)

comaniac commented on a change in pull request #6302: URL: https://github.com/apache/incubator-tvm/pull/6302#discussion_r476620163 ## File path: python/tvm/driver/tvmc/compiler.py ## @@ -0,0 +1,407 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more cont

[GitHub] [incubator-tvm] comaniac commented on a change in pull request #6302: [tvmc] command line driver 'compile' (part 2/4)

comaniac commented on a change in pull request #6302: URL: https://github.com/apache/incubator-tvm/pull/6302#discussion_r476617797 ## File path: python/tvm/driver/tvmc/compiler.py ## @@ -0,0 +1,407 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more cont

[GitHub] [incubator-tvm] comaniac commented on a change in pull request #6302: [tvmc] command line driver 'compile' (part 2/4)

comaniac commented on a change in pull request #6302: URL: https://github.com/apache/incubator-tvm/pull/6302#discussion_r476610879 ## File path: python/tvm/driver/tvmc/compiler.py ## @@ -0,0 +1,407 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more cont

[GitHub] [incubator-tvm] kparzysz-quic commented on a change in pull request #6331: [TESTS] Refactor tests to run on either the GPU or CPU

kparzysz-quic commented on a change in pull request #6331: URL: https://github.com/apache/incubator-tvm/pull/6331#discussion_r476604609 ## File path: python/tvm/testing.py ## @@ -285,4 +288,184 @@ def _check_forward(constraints1, constraints2, varmap, backvarmap):

[GitHub] [incubator-tvm] comaniac commented on a change in pull request #6302: [tvmc] command line driver 'compile' (part 2/4)

comaniac commented on a change in pull request #6302: URL: https://github.com/apache/incubator-tvm/pull/6302#discussion_r476609291 ## File path: python/tvm/driver/tvmc/compiler.py ## @@ -0,0 +1,407 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more cont

[GitHub] [incubator-tvm] comaniac commented on a change in pull request #6302: [tvmc] command line driver 'compile' (part 2/4)

comaniac commented on a change in pull request #6302: URL: https://github.com/apache/incubator-tvm/pull/6302#discussion_r476606729 ## File path: python/tvm/driver/tvmc/compiler.py ## @@ -0,0 +1,407 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more cont

[GitHub] [incubator-tvm] comaniac commented on a change in pull request #6310: [Ansor][AutoTVM v2.0] Phase 2: Evolutionary Search

comaniac commented on a change in pull request #6310: URL: https://github.com/apache/incubator-tvm/pull/6310#discussion_r476605391 ## File path: tests/python/unittest/test_auto_scheduler_evolutionary_search.py ## @@ -0,0 +1,35 @@ +# Licensed to the Apache Software Foundation (A

[GitHub] [incubator-tvm] tkonolige commented on a change in pull request #6331: [TESTS] Refactor tests to run on either the GPU or CPU

tkonolige commented on a change in pull request #6331: URL: https://github.com/apache/incubator-tvm/pull/6331#discussion_r476597060 ## File path: tests/scripts/setup-pytest-env.sh ## @@ -26,5 +26,20 @@ else fi set -u +export TVM_TEST_DEVICES="" +while test $# -gt 0 +do +

[GitHub] [incubator-tvm] mbrookhart commented on a change in pull request #6316: Dynamic Strided Slice

mbrookhart commented on a change in pull request #6316: URL: https://github.com/apache/incubator-tvm/pull/6316#discussion_r476576161 ## File path: python/tvm/relay/op/transform.py ## @@ -827,13 +828,17 @@ def strided_slice(data, begin, end, strides=None, slice_mode="end"):

[incubator-tvm] branch master updated (0466d60 -> 751982e)

This is an automated email from the ASF dual-hosted git repository. haichen pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from 0466d60 [BYOC][ACL] Enable remote device via environment variables (#6279) add 751982e [FIX][VM] Fix

[GitHub] [incubator-tvm] icemelon9 commented on pull request #6322: [FIX][VM] Fix relay vm optimize

icemelon9 commented on pull request #6322: URL: https://github.com/apache/incubator-tvm/pull/6322#issuecomment-680120184 Thanks @zhiics This is an automated message from the Apache Git Service. To respond to the message, ple

[GitHub] [incubator-tvm] icemelon9 merged pull request #6322: [FIX][VM] Fix relay vm optimize

icemelon9 merged pull request #6322: URL: https://github.com/apache/incubator-tvm/pull/6322 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 t

[incubator-tvm] branch master updated (a189fe0 -> 0466d60)

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 a189fe0 [Frontend][Relay] Keras softmax and prelu fix (#6278) (#6278) add 0466d60 [BYOC][ACL] Enable remo

[GitHub] [incubator-tvm] zhiics merged pull request #6279: [BYOC][ACL] Enable remote device via environment variables

zhiics merged pull request #6279: URL: https://github.com/apache/incubator-tvm/pull/6279 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 g

[GitHub] [incubator-tvm] zhiics commented on pull request #6279: [BYOC][ACL] Enable remote device via environment variables

zhiics commented on pull request #6279: URL: https://github.com/apache/incubator-tvm/pull/6279#issuecomment-680118504 Thanks @lhutton1 @comaniac @leandron This is an automated message from the Apache Git Service. To respond

[GitHub] [incubator-tvm] tqchen commented on pull request #6206: [Caffe Frontend] introduce caffe frontend for tvm

tqchen commented on pull request #6206: URL: https://github.com/apache/incubator-tvm/pull/6206#issuecomment-680094157 @fernchen please try to send another dummy commit to retrigger the CI, @FrozenGene please followup. I think we can merge once all the tests are resolved -

[GitHub] [incubator-tvm] mbaret opened a new pull request #6335: [BYOC][ETHOSN] Add support for quantized convolution

mbaret opened a new pull request #6335: URL: https://github.com/apache/incubator-tvm/pull/6335 This PR adds support for quantized convolution for the Ethos-N backend. This includes mapping it via a composite function and all the necessary methods to convert from Relay to the APIs in Suppor

[GitHub] [incubator-tvm] ANSHUMAN87 commented on a change in pull request #6238: [TIR][Transform]Block scope hoisting added

ANSHUMAN87 commented on a change in pull request #6238: URL: https://github.com/apache/incubator-tvm/pull/6238#discussion_r476500914 ## File path: tests/python/unittest/test_tir_transform_hoist_if.py ## @@ -255,6 +259,488 @@ def test_multi_if(): ('tir.Fo

[GitHub] [incubator-tvm] MarisaKirisame commented on pull request #6238: [TIR][Transform]Block scope hoisting added

MarisaKirisame commented on pull request #6238: URL: https://github.com/apache/incubator-tvm/pull/6238#issuecomment-680016599 @ANSHUMAN87 please rebase and fix the CI. This is an automated message from the Apache Git Service.

[GitHub] [incubator-tvm] MarisaKirisame commented on pull request #6326: [Relay] Make check stricter by using Feature. Fixed multiple bugs.

MarisaKirisame commented on pull request #6326: URL: https://github.com/apache/incubator-tvm/pull/6326#issuecomment-679948905 @wweic @vinx13 can you guys review? This is an automated message from the Apache Git Service. To re

[GitHub] [incubator-tvm] leandron commented on a change in pull request #6333: Add docker/lint.sh, for running dockerized lint scripts locally

leandron commented on a change in pull request #6333: URL: https://github.com/apache/incubator-tvm/pull/6333#discussion_r476325378 ## File path: tests/lint/filter_untracked.py ## @@ -0,0 +1,60 @@ +#!/usr/bin/env python3 +# Licensed to the Apache Software Foundation (ASF) under

  1   2   >