[Apache TVM Discuss] [Development/RFC] RFC: Introduce automatic formatting of Python code

2020-09-08 Thread Junru Shao via Apache TVM Discuss
+1 it will be super nice! Personally when using vscode, I use the black integration with “format on save” to make sure the code is formatted well. It will be great if we provide those tooling instructions in the documentation page as well. --- [Visit Topic](https://discuss.tvm.apache.org

[Apache TVM Discuss] [Development] Make binary distributation

2020-09-10 Thread Junru Shao via Apache TVM Discuss
I believe @haichen and @tqchen are actively working on this. --- [Visit Topic](https://discuss.tvm.apache.org/t/make-binary-distributation/7867/3) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm

[Apache TVM Discuss] [Development/RFC] [RFC] tlcpack: Thirdparty Binary Packages

2020-09-14 Thread Junru Shao via Apache TVM Discuss
Finally! Thank you for the hard work!! --- [Visit Topic](https://discuss.tvm.apache.org/t/rfc-tlcpack-thirdparty-binary-packages/7903/2) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.apache.or

[Apache TVM Discuss] [Development/RFC] [RFC] Rename Hybrid Script

2020-09-15 Thread Junru Shao via Apache TVM Discuss
CC: @spectrometerHBH @Hzfengsy @were --- [Visit Topic](https://discuss.tvm.apache.org/t/rfc-rename-hybrid-script/7915/2) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.apache.org/email/unsubscri

[Apache TVM Discuss] [Development/RFC] Append a custom target for TVM Context

2020-09-17 Thread Junru Shao via Apache TVM Discuss
I saw FunctionInfo in the unmangled symbol name, so it looks like there are some missing pieces in the build. Seems like some linking issues or some symbols are missing. Is it working if you build on HEAD? --- [Visit Topic](https://discuss.tvm.apache.org/t/append-a-custom-target-for-tvm-

[Apache TVM Discuss] [Development/RFC] [RFC] TensorIR: A schedulable IR for TVM

2020-09-21 Thread Junru Shao via Apache TVM Discuss
@xqdan Thank you for the valuable feedback! Fusion can be done automatically with some analysis provided in Ansor. Do you have any other kind of analysis in mind that might be potentially useful? --- [Visit Topic](https://discuss.tvm.apache.org/t/rfc-tensorir-a-schedulable-ir-for-tvm/7872

[Apache TVM Discuss] [Development/RFC] [RFC] Differentiable tensor expression (Create and verify backward op automatically)

2020-09-21 Thread Junru Shao via Apache TVM Discuss
Hey @wrongtest, Thank you for the RFC! Just wondering how it compares with the previous AD RFC (https://discuss.tvm.apache.org/t/rfc-bring-in-tensor-expression-autodiff/5987) ? Thanks! --- [Visit Topic](https://discuss.tvm.apache.org/t/rfc-differentiable-tensor-expression-create-and-veri

[Apache TVM Discuss] [Development/RFC] [RFC] TensorIR: A schedulable IR for TVM

2020-09-21 Thread Junru Shao via Apache TVM Discuss
@xqdan In Ansor, Fusion analysis is handled in TE with some straightforward heuristics, which I believe have covered our usecases. CC: @merrymercy @jcf94 Agree that ISL provides effective information about vectorization, and I believe there might be other competitive heuristics too. Tensorizat

[Apache TVM Discuss] [Development/RFC] [RFC] Differentiable tensor expression (Create and verify backward op automatically)

2020-09-21 Thread Junru Shao via Apache TVM Discuss
CC: @yzhliu the major contributor of this feature --- [Visit Topic](https://discuss.tvm.apache.org/t/rfc-differentiable-tensor-expression-create-and-verify-backward-op-automatically/7960/4) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from thes

[Apache TVM Discuss] [Development/RFC] [RFC] TensorIR: A schedulable IR for TVM

2020-09-21 Thread Junru Shao via Apache TVM Discuss
@merrymercy I didn't get it about batched bound inference, doesn't Ansor use a pool of threads for massive bound inference? --- [Visit Topic](https://discuss.tvm.apache.org/t/rfc-tensorir-a-schedulable-ir-for-tvm/7872/35) to respond. You are receiving this because you enabled mailing lis

[Apache TVM Discuss] [Development] Linalg support for matrix determinant and inverse

2020-09-23 Thread Junru Shao via Apache TVM Discuss
For now, we can support linalg via TVM external functions: https://tvm.apache.org/docs/tutorials/language/extern_op.html#sphx-glr-tutorials-language-extern-op-py. --- [Visit Topic](https://discuss.tvm.apache.org/t/linalg-support-for-matrix-determinant-and-inverse/7973/2) to respond. You

[Apache TVM Discuss] [Development] Linalg support for matrix determinant and inverse

2020-09-23 Thread Junru Shao via Apache TVM Discuss
In this case, you may link the code into tvm_runtime, expose them with TVM_REGISTER_GLOBAL (i.e. as a packed function), then they can be used as tvm.extern. Example: https://github.com/apache/incubator-tvm/blob/master/src/runtime/contrib/nnpack/fully_connected.cc#L36 --- [Visit Topic](ht

[Apache TVM Discuss] [Development/RFC] [RFC] tlcpack: Thirdparty Binary Packages

2020-09-24 Thread Junru Shao via Apache TVM Discuss
BTW, @haichen shall we also release runtime-only version of tlcpack? It would be helpful if people want to bake TVM-compiled operators in other frameworks shallowly in python --- [Visit Topic](https://discuss.tvm.apache.org/t/rfc-tlcpack-thirdparty-binary-packages/7903/8) to respond. Yo

[Apache TVM Discuss] [Development] Running TVM on FreeBSD

2020-09-27 Thread Junru Shao via Apache TVM Discuss
Using CXX is a good idea IMO. Would you love to send a PR? Thanks! --- [Visit Topic](https://discuss.tvm.apache.org/t/running-tvm-on-freebsd/8009/2) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tv

[Apache TVM Discuss] [Development] Running TVM on FreeBSD

2020-09-29 Thread Junru Shao via Apache TVM Discuss
Would you love to send a quick PR on GitHub so that we can merge the patch in? Thanks! --- [Visit Topic](https://discuss.tvm.apache.org/t/running-tvm-on-freebsd/8009/5) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click her

[Apache TVM Discuss] [Development/RFC] [RFC] CSE Optimization

2020-10-16 Thread Junru Shao via Apache TVM Discuss
I agree with @tqchen. CSE is not hard to implement, and CSE on both sides provides different benefits. So we can potentially support both variants. --- [Visit Topic](https://discuss.tvm.apache.org/t/rfc-cse-optimization/8130/6) to respond. You are receiving this because you enabled mailin

[Apache TVM Discuss] [Development/RFC] [RFC] A general task extraction mechanism for auto_scheduler

2020-11-12 Thread Junru Shao via Apache TVM Discuss
CC: @Hzfengsy @spectrometerHBH if you guys are interested --- [Visit Topic](https://discuss.tvm.apache.org/t/rfc-a-general-task-extraction-mechanism-for-auto-scheduler/8444/6) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [cli

[Apache TVM Discuss] [Development/RFC] [RFC] Rename TVMContext to TVMDevice

2021-02-07 Thread Junru Shao via Apache TVM Discuss
Thanks for bringing this up! Context is indeed a bad name when it is used to indicate a certain device, because its meaning really varies depending on the “context”. In this case, “device” is certainly an acceptable name and is a lot better than “context”. Two thoughts: 1) when referring to a

[Apache TVM Discuss] [Development/RFC] [RFC] Rename TVMContext to TVMDevice

2021-02-08 Thread Junru Shao via Apache TVM Discuss
Yeah this change sounds quite reasonable to me. BTW, the DLPack case might be a bit intricate, because it needs consensus across different frameworks, but let's leave the discussion to DLPack RFC :slight_smile: --- [Visit Topic](https://discuss.tvm.apache.org/t/rfc-rename-tvmcontext-to-tv

[Apache TVM Discuss] [Development/RFC] [RFC] Rename TVMContext to TVMDevice

2021-02-09 Thread Junru Shao via Apache TVM Discuss
My take on dropping the TVM prefix: given DLTensor/DLContext is the de facto standard, we do not really need to define their TVM alias (e.g. TVMContext) and can just use them directly --- [Visit Topic](https://discuss.tvm.apache.org/t/rfc-rename-tvmcontext-to-tvmdevice/9090/11) to respon

[Apache TVM Discuss] [Development/RFC] Thoughts on a Simpler Scheduling Language

2021-02-10 Thread Junru Shao via Apache TVM Discuss
Hey @srush, Thanks for asking! We are actively developing a more straightforward scheduling language and a new IR called TensorIR: * imperative scheduling: each schedule primitive is like applying a compiler pass that transforms the TensorIR to a new TensorIR - you can see and debug the sch

[Apache TVM Discuss] [Development/RFC] [RFC] TensorIR: A schedulable IR for TVM

2021-02-11 Thread Junru Shao via Apache TVM Discuss
Hey @srush, Thanks for your valuable feedback! Please allow me to try to explain the design rationale below: > **Q1.** There are strings for get_block? Yeah. One design principle we hold for TensorIR is that all needed for scheduling is contained in the TensorIR python syntax, so that there

[Apache TVM Discuss] [Development/RFC] [RFC] TensorIR: A schedulable IR for TVM

2021-02-13 Thread Junru Shao via Apache TVM Discuss
> I’m still stuck on reverse_compute_at which seems like a long name, and is > still a bit too magical for me to understand Yeah I once had some discussion with @tqchen and @spectrometerHBH that reverse_compute_at is too long and tedious, and I agree it will be great to find some better names

[Apache TVM Discuss] [Development] Debugging libtvm.so

2021-02-15 Thread Junru Shao via Apache TVM Discuss
In TVM we can define our own ReprPrinter for different subclasses of ObjectRef. Try `LOG(INFO) << some_object_ref` --- [Visit Topic](https://discuss.tvm.apache.org/t/debugging-libtvm-so/9134/2) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from

[Apache TVM Discuss] [Development/RFC] [RFC] TensorIR: A schedulable IR for TVM

2021-02-15 Thread Junru Shao via Apache TVM Discuss
Thanks @srush! I totally agree! Simplifying the scheduling language is definitely an important issue, especially when we want to approach broader audience. An idea to make it happen is to compose schedule "primitives" into more high-level "composite rules". For example, making "tiling + cache

[Apache TVM Discuss] [Development/RFC] [RFC] Setting up Mypy type checking for TVM codebase

2021-03-02 Thread Junru Shao via Apache TVM Discuss
@jroesch Is there anything we can do in the CI to enforce type annotation for new code? --- [Visit Topic](https://discuss.tvm.apache.org/t/rfc-setting-up-mypy-type-checking-for-tvm-codebase/9231/12) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe

[Apache TVM Discuss] [Development/RFC] [RFC] Rename TVMContext to TVMDevice

2021-03-03 Thread Junru Shao via Apache TVM Discuss
I vote for A0 after careful consideration. DLDevice requires extra knowledge of DLPack --- [Visit Topic](https://discuss.tvm.apache.org/t/rfc-rename-tvmcontext-to-tvmdevice/9090/25) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these email

[Apache TVM Discuss] [Development/RFC] [RFC] TensorIR: A schedulable IR for TVM

2021-03-29 Thread Junru Shao via Apache TVM Discuss
Yeah, to fully replace IRBuilder, there are still some missing elements of TVM script: meta programming and hygiene macros. Let's consider the support after the upstreaming is done :-) CC @tqchen --- [Visit Topic](https://discuss.tvm.apache.org/t/rfc-tensorir-a-schedulable-ir-for-tvm/787

[Apache TVM Discuss] [Development/RFC] [RFC] TensorIR: A schedulable IR for TVM

2021-03-29 Thread Junru Shao via Apache TVM Discuss
@masahi Yeah. We should allow to embed IR fragments, functions that produce IR fragments, or replace some tokens with caller specified IR fragments into the script :-) --- [Visit Topic](https://discuss.tvm.apache.org/t/rfc-tensorir-a-schedulable-ir-for-tvm/7872/61) to respond. You are r

[Apache TVM Discuss] [Development] NDArray conversion to numpy array take time (around 350ms) with a simple data

2021-03-31 Thread Junru Shao via Apache TVM Discuss
Yeah here is the example: https://github.com/dmlc/dlpack/tree/main/apps/from_numpy. Note that we assume the array is on CPU because numpy arrays are cpu-only. --- [Visit Topic](https://discuss.tvm.apache.org/t/ndarray-conversion-to-numpy-array-take-time-around-350ms-with-a-simple-data/605

[Apache TVM Discuss] [Development/RFC] Pass Instrument Framework Proposal

2021-04-30 Thread Junru Shao via Apache TVM Discuss
Also CC @zhiics @zxybazh @vinx13 --- [Visit Topic](https://discuss.tvm.apache.org/t/pass-instrument-framework-proposal/9874/3) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.apache.org/email/un

[Apache TVM Discuss] [Development/RFC] [RFC] Register OPs from python site and followup

2021-05-06 Thread Junru Shao via Apache TVM Discuss
Right now we allow adding attributes of operators in python: https://github.com/apache/tvm/blob/main/src/ir/op.cc#L105. I suspect that we don't have a public API to add operators on the python side right now, and I don't know the reason why not. If you wanted to, you may just expose `OpRegEnt

[Apache TVM Discuss] [Announcement] [Announce] New TVM Community Calendar

2021-05-28 Thread Junru Shao via Apache TVM Discuss
Thanks Chris! It is much more convenient :-) --- [Visit Topic](https://discuss.tvm.apache.org/t/announce-new-tvm-community-calendar/10111/2) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.apach

[Apache TVM Discuss] [Development/pre-RFC] [RFC] Meta Schedule

2021-05-28 Thread Junru Shao via Apache TVM Discuss
# [RFC] Meta Schedule * Feature Name: Meta Schedule * Start Date: 2021-05-28 * RFC PR: TBD (apache/tvm-rfcs#) * GitHub Issue: TBD (apache/tvm-rfcs#) ## 1. Summary This proposal introduces Meta Schedule: a probabilistic scheduling DSL on TIR that unifies the approaches of AutoTVM and A

[Apache TVM Discuss] [Development/pre-RFC] [RFC] Better type hinting for TVM scripts

2021-08-01 Thread Junru Shao via Apache TVM Discuss
Thanks for the proposal! It is definitely extremely important for us to have better type hints and documents for TVM scripts. One quick question I have been thinking of: is it possible to unify and prevent divergence between `tir.XXX` in the script and `tvm.tir` namespace? If so, there probab

[Apache TVM Discuss] [Development/pre-RFC] [RFC] Setting up Mypy type checking for TVM codebase

2021-08-01 Thread Junru Shao via Apache TVM Discuss
@Wheest I am not super certain if there is a fully automated process given our current docstring-based type annotation may be casual or inaccurate, but it is definitely doable if we could call for community contribution :-) --- [Visit Topic](https://discuss.tvm.apache.org/t/rfc-setting-up

[Apache TVM Discuss] [Development/pre-RFC] New Target Intrinsic Lowering and Legalization Mechanism

2021-08-05 Thread Junru Shao via Apache TVM Discuss
@kparzysz Thanks for asking! For example, there might be some rare TVM intrinsics like `tir.erf` that may be lowered to some cuda intrinsic (using `Lowering`), but those intrinsics aren't guaranteed to exist on other hardware platforms, and in this case, we substitute the intrinsic with more c

[Apache TVM Discuss] [Development] Is there a difference between "lower" and "legalize" in TIR?

2021-08-05 Thread Junru Shao via Apache TVM Discuss
Sorry I was posting on a wrong thread @kparzysz Thanks for asking! For example, there might be some rare TVM intrinsics like `tir.erf` that may be lowered to some cuda intrinsic (using `Lowering`), but those intrinsics aren't guaranteed to exist on other hardware platforms, and in this case,

[Apache TVM Discuss] [Development/pre-RFC] Updated Docs pre-RFC

2021-08-18 Thread Junru Shao via Apache TVM Discuss
CC @jroesch @tqchen @zhiics @ziheng @yzhliu @masahi @thierry @haichen @Laurawly @merrymercy @comaniac @FrozenGene @jcf94 As we are pushing for major doc refactoring work, we would love to hear more from the community on the desirable doc structure, which is vital for our community in terms o

[Apache TVM Discuss] [Development/pre-RFC] Updated Docs pre-RFC

2021-08-19 Thread Junru Shao via Apache TVM Discuss
I would prefer L2 in terms of more precise section titles. Sometimes it is really hard to distinguish "User Guide" and "Developer Guide", and L2 replaces them with more explicit terms "Tutorials by example", "Architectural guide by each component of TVM system". The only thing missing here is

[Apache TVM Discuss] [Development/pre-RFC] [RFC] TVM Target Specification

2021-08-22 Thread Junru Shao via Apache TVM Discuss
Thanks @mbs-octoml! `Target` is a compile-time concept, while `device` is a runtime concept. The separation design is to make sure that a target can describe a device that doesn't exist on the host, mainly for cross compilation. And yes, in principle, every `TargetKind` corresponds to a `DLDe

[Apache TVM Discuss] [Development/pre-RFC] [RFC] TVM Target Specification

2021-08-22 Thread Junru Shao via Apache TVM Discuss
In other words, in compile time, IIUC we should replace `DLDeviceType` with `TargetKind` --- [Visit Topic](https://discuss.tvm.apache.org/t/rfc-tvm-target-specification/6844/60) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [

[Apache TVM Discuss] [Development/pre-RFC] [pre-RFC] Compilation Configuration Representation

2021-11-03 Thread Junru Shao via Apache TVM Discuss
Thank you @Mousius for the RFC! It's great to read about potential user experience issues of the current Target system, and happy to discuss about potential ways to improve it. ## Proposeds API in the RFC `CompilationConfig`, as proposed in this RFC, aims to improve UX by wrapping a list of

[Apache TVM Discuss] [Development/pre-RFC] [pre-RFC] Compilation Configuration Representation

2021-11-11 Thread Junru Shao via Apache TVM Discuss
@areusch and I had long discussion yesterday offline, and he helped me understand the concern from the UX perspective: If we fold executor into target, then it's more difficult to separate the config coming from two parties, where one party impl the codegen and the other impl the executor. On

[Apache TVM Discuss] [Development/pre-RFC] [pre-RFC] Compilation Configuration Representation

2021-11-11 Thread Junru Shao via Apache TVM Discuss
@Mousius I totally agree to make things hygiene, and believe folding things into Target is the correct and consistent approach. First of all, the automation system solely relies on the target object to understand the code dispatching, hardware specs and runtime information. Without having the

[Apache TVM Discuss] [Development/pre-RFC] [pre-RFC] Compilation Configuration Representation

2021-11-11 Thread Junru Shao via Apache TVM Discuss
What about we define a new target kind: ``` { "kind": "packaged", # probably need a better name, please propose new ones "runtime": "crt", # the "runtime" in the proposal "executor": { # the codegen target for relay function # i.e. the "executor" in the propos

[Apache TVM Discuss] [Development/pre-RFC] [DISCUSS] Embed more Bound Information into Var or Expr

2021-11-18 Thread Junru Shao via Apache TVM Discuss
using assert_stmt is a valid approach --- [Visit Topic](https://discuss.tvm.apache.org/t/discuss-embed-more-bound-information-into-var-or-expr/4079/31) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discus

[Apache TVM Discuss] [Development/pre-RFC] [DISCUSS] Embed more Bound Information into Var or Expr

2021-11-18 Thread Junru Shao via Apache TVM Discuss
It's not supported yet in TensorIR, but will be a good thing to have in the future :-) --- [Visit Topic](https://discuss.tvm.apache.org/t/discuss-embed-more-bound-information-into-var-or-expr/4079/33) to respond. You are receiving this because you enabled mailing list mode. To unsubscri

[Apache TVM Discuss] [Development/pre-RFC] Tvm integration with external DSP accelerator API

2021-12-06 Thread Junru Shao via Apache TVM Discuss
Looks like it could be abstracted as calling a packed function...On the low-level you may use `call_packed` as demonstrated [here](https://github.com/apache/tvm/blob/main/tests/python/unittest/test_te_tensor.py#L187); CC @yuchenj on the high-level IR --- [Visit Topic](https://discuss.tvm

[Apache TVM Discuss] [Development/pre-RFC] [RFC] Better tvm logger in C++ side

2021-12-19 Thread Junru Shao via Apache TVM Discuss
This is definitely extremely important! I would love to further discuss with you on the environment variables used here. Do you think it’s possible to unify DMLC_ and TVM_ environment variables? Is it possible to minimize the number of env variables to use? Is there any precedent we could refe

[Apache TVM Discuss] [Development/pre-RFC] [RFC] Better tvm logger in C++ side

2021-12-19 Thread Junru Shao via Apache TVM Discuss
Another idea @zxybazh and I have been discussing is the possibility to unify Python and CXX logging system via packed functions, i.e. the CXX logging system could potentially call back to python's logging module --- [Visit Topic](https://discuss.tvm.apache.org/t/rfc-better-tvm-logger-in-c

[Apache TVM Discuss] [Development/pre-RFC] [RFC][TOP][BYOC] Intel LIBXSMM Integration

2022-01-01 Thread Junru Shao via Apache TVM Discuss
Shall we conclude this pre-RFC and send a formal RFC to https://github.com/apache/tvm-rfcs/? --- [Visit Topic](https://discuss.tvm.apache.org/t/rfc-top-byoc-intel-libxsmm-integration/11688/15) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from

[Apache TVM Discuss] [Development/pre-RFC] Bring `PackedFunc` into TVM Object System

2022-01-01 Thread Junru Shao via Apache TVM Discuss
I'm happy to shepherd this RFC CC: @spectrometerHBH @tqchen @areusch --- [Visit Topic](https://discuss.tvm.apache.org/t/bring-packedfunc-into-tvm-object-system/11816/2) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click he

[Apache TVM Discuss] [Development/pre-RFC] [RFC][TOP][BYOC] Intel LIBXSMM Integration

2022-01-03 Thread Junru Shao via Apache TVM Discuss
Yeah I was on vacation and didn't track closely. Sorry for the confusion! --- [Visit Topic](https://discuss.tvm.apache.org/t/rfc-top-byoc-intel-libxsmm-integration/11688/18) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click

[Apache TVM Discuss] [Development/pre-RFC] [RFC][Runtime] Bring `PackedFunc` into TVM Object System

2022-01-03 Thread Junru Shao via Apache TVM Discuss
To summarize our offline discussion with @areusch @tqchen. Clarification: 1. This RFC doesn't change any of the existing functionality, including C ABI or PackedFunc's C++ API. Any modification to the C ABI is out of scope of this RFC. 2. Calling a PackedFunc inside TVM codebase directly uses

[Apache TVM Discuss] [Development/pre-RFC] [RFC][Runtime] Bring `PackedFunc` into TVM Object System

2022-01-03 Thread Junru Shao via Apache TVM Discuss
Let's leave this pre-RFC open for a week, and then send a formal RFC with clarifications to https://github.com/apache/tvm-rfcs/ --- [Visit Topic](https://discuss.tvm.apache.org/t/rfc-runtime-bring-packedfunc-into-tvm-object-system/11816/8) to respond. You are receiving this because you e

[Apache TVM Discuss] [Development/pre-RFC] [RFC][Runtime] Bring `PackedFunc` into TVM Object System

2022-01-04 Thread Junru Shao via Apache TVM Discuss
@cxy would you like to update the pre-RFC according to our discussion? Thanks a lot! --- [Visit Topic](https://discuss.tvm.apache.org/t/rfc-runtime-bring-packedfunc-into-tvm-object-system/11816/9) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe f

[Apache TVM Discuss] [Development/pre-RFC] [RFC]FamilySeer: A new search method for Auto-scheduler

2022-01-07 Thread Junru Shao via Apache TVM Discuss
Thanks for the proposal! We are very interested in improving search algorithms and cost model. I was very excited to read about FamilySeer a week ago. In terms of the subgraph similarity, AFAIK @comaniac and @zxybazh have been working independently on this topic to improve overall search time

[Apache TVM Discuss] [Development] Can we lift tir.AttrStmt value type to ObjectRef?

2022-02-18 Thread Junru Shao via Apache TVM Discuss
[quote="wrongtest, post:1, topic:12118"] But certain pragma annotations can not get lowerer to `T.attr`,only those of expression typed values are allowed [/quote] Would you like to elaborate? Currently the type of `AttrStmtNode::value` is `PrimExpr`, but which type cannot be supported by TVMSc

[Apache TVM Discuss] [Development] Can we lift tir.AttrStmt value type to ObjectRef?

2022-02-18 Thread Junru Shao via Apache TVM Discuss
This is definitely interesting usecases which unifies "AttrStmt" with definitions of Attr otherwhere in the codebase. Given `AttrStmt` is something we wanted to move away from, I would love to confirm with @tqchen that the change is acceptable --- [Visit Topic](https://discuss.tvm.apache

[Apache TVM Discuss] [Development/pre-RFC] [RFC] Remove CODEOWNERS

2022-02-22 Thread Junru Shao via Apache TVM Discuss
It definitely makes sense for us to reduce the traffic from the github emails. Github teams is definitely a good idea. I'm supportive 👍 --- [Visit Topic](https://discuss.tvm.apache.org/t/rfc-remove-codeowners/12095/4) to respond. You are receiving this because you enabled mailing list mod

[Apache TVM Discuss] [Development/pre-RFC] [RFC] TVMScript Metaprogramming

2022-06-17 Thread Junru Shao via Apache TVM Discuss
How about we consolidate our discussion to the RFC thread (https://github.com/apache/tvm-rfcs/pull/79) so that people can see what's happening in a centralized place? --- [Visit Topic](https://discuss.tvm.apache.org/t/rfc-tvmscript-metaprogramming/12969/4) to respond. You are receiving

[Apache TVM Discuss] [Development] Modularize and Modernize TensorIR Tests

2023-07-02 Thread Junru Shao via Apache TVM Discuss
It is worth pointing out that: * Most of the existing tests are CPU-bound, including those uses GPU for execution (end-to-end tests), which also relies heavily on CPU for code generation * All e2e tests can be decoupled as host-side compilation on CPU + execution on device (e.g. GPUs) * Brute

[Apache TVM Discuss] [Development] [Design] Torchy: Productive Model Definition in TVM Unity

2023-07-31 Thread Junru Shao via Apache TVM Discuss
A full-featured Llama2 implementation in only 200 lines of code based on this project: https://github.com/mlc-ai/mlc-llm/pull/631 --- [Visit Topic](https://discuss.tvm.apache.org/t/design-torchy-productive-model-definition-in-tvm-unity/15404/2) to respond. You are receiving this because