The new cases added for quantized matmuls are:
1. vec-vec
2. vec-mat
3. mat-vec
each of which are now lowered to expand(s), quantized_matmul, and
collapse.
1. onnx.MatMulInteger now converts to aten.matmul instead of aten.mm
2. aten.matmul, for ranks >=2, now allows quantized inputs and will
lower to linalg::quantized_matmul or linalg::quantized_batch_matmul.
3. added AtenMatmulOp to the FuseQuantizeOps rewrite patters
QuantizeOperands, QuantizeTransposedOperands, and QuantizeAccumulator
4. added several tests, including some to test AtenMmOp with varying
quantization signed-ness.
5. a quantized matmul mat-vec test is added to verify the failure to
lower to linalg; cleaned of out-of-date code related to common
torch-mlir lowering xfails.
6. in debugging a real model with quantized matmuls, I found a bug on
the scalarize-shapes pass which resulted from the aten.full op folder
returning an incompatible result type. This is fixed by the small change
here to
[lib/Dialect/Torch/IR/TorchOps.cpp](https://github.com/llvm/torch-mlir/compare/main...zjgarvey:torch-mlir:MatMulIntegerFix?expand=1#diff-dc8ed165c207918e606490eee3984b1ad51d7034e6aac36fc046bf47f6f03f4f).
- Added linalg lowering for `AtenFloorDivideScalarOp`
- Needed `AtenDivScalarModeOp` for the decomp.
- Added linalg lowering for `AtenDivScalarModeOp`
- Moved linalg payload logic to `createDivModePayload()` since the logic
was nearly identical for both `AtenDivScalarModeOp` and
`AtenDivTensorModeOp`. Just a template function
- Added `AtenDivScalarModeOp` lowering for stablehlo
Pytorch's
[`torch.floor_divide()`](https://pytorch.org/docs/stable/generated/torch.floor_divide.html)
in a previous version (for a reason unknown to me) preformed a
truncation instead of "floor". The already implemented op
`AtenFloorDivideTensorOp` was done before this change. However, this
wasn't caught because our testcases only tested positive floor division.
I changed this to floor as well as adding a few test cases.
If there is only a single value scattered there can be an implicit batch
dimension. This includes a check for the implicit batch dimension when
reshaping the update tensor. It includes an e2e test to verify
correctness.
Fix the case PrimListUnpackOp's result num is not equal to PrimList
length.
See the following example:
```python
def forward(self, x):
if len(x.shape) == 5:
b0, t, c0, h0, w0 = x.shape
b, c, h, w = torch.mul(b0, t), c0, h0, w0
else:
b1, c1, h1, w1 = x.shape
b, c, h, w = b1, c1, h1, w1
res = torch.reshape(x, [b, c, h, w])
return res
```
Without this fix, the following error message will occur：
```
/root/torch-mlir/externals/llvm-project/mlir/lib/IR/PatternMatch.cpp:118: virtual void mlir::RewriterBase::replaceOp(mlir::Operation *, mlir::ValueRange): Assertion `op->getNumResults() == newValues.size() && "incorrect # of replacement values"' failed.
```
Previously, it could only handle the situations where outputsize == (1,
1) or outputsize == (input_H, input_W). Now it supports all situations
where input_H % output_H== 0 && input_W % output_W == 0
1. Changes the linalg lowering for dequantization ops to always sign
cast to float to prevent misrepresenting uint32 overflow on subtraction
with zero point.
2. Adds a basic quantized model test which only quantizes and
dequantizes and now passes with these changes in linalg and onnx
configs.
3. Changes the aten.mm lowering to allow mismatched quantized types.
4. If a quantized matmul arg is uint8, we shift by 128 to faithfully
represent the quantization as a signed i8 quantization. This worked fine
in the AtenMmOp lowering, but I'd be happy to move it to a rewrite in
FuseQuantizedOps.cpp instead if that seems more appropriate.
With the changes 3 and 4, the QuantizedMLP_basic and
QuantizedSingleLayer_basic e2e tests now passes with the onnx config.
They replaced all `c10::optional` usages with `std::optional` in
torchgen'd code in
fb90b4d4b2
causing the LTC build to break.
Replacing all usages of `c10::optional` with `std::optional` in
`projects/ltc` has fixed the issue
Issue: #3120
Added error message when adding new torch op to
[torch_ods_gen.py](https://github.com/llvm/torch-mlir/compare/main...IanWood1:torch-mlir:ods_gen_error_message?expand=1#diff-889b60b904ed67a5065a14e8de6fc89e00e199577e4d2bfa134ac4d1c89832d2).
New message displays which op key is failing and possible matches in the
torch `Registry`.
```Op does not match any Torch ops in Registry
Given op:
"aten::hardtanh_wrong : (Tensor, Scalar) -> (Tensor)"
Possible matches:
"aten::hardshrink : (Tensor, Scalar) -> (Tensor)"
"aten::hardtanh_ : (Tensor, Scalar, Scalar) -> (Tensor)"
"aten::hardtanh : (Tensor, Scalar, Scalar) -> (Tensor)"
"aten::clamp_min : (Tensor, Scalar) -> (Tensor)"
"aten::linalg_cond : (Tensor, Scalar?) -> (Tensor)"```
Also, ran black formatting on file. Based on LLVM style guides this seems to be correct, but I can revert the formatting if needed.
This PR only performs a lit test. In lieu of an e2e test, https://github.com/nod-ai/SHARK-TestSuite/pull/142 makede sure that the lowering works & the numbers check out.
Co-authored-by: Xida Ren <xida.ren.dev@gmail.com>
Shapes can be processed as tensors to represent the set of dimensions.
As reshapes take a list of scalars this can result in a single dynamic
dimension blocking the adjacent static dimensions.
This pass attempts to de-couple tensor computations related to shapes
and propagate values to better support lowering scalar tensor
computations.
There is an issue with stablehlo's linalg compilation. Canonicalization
appears to cleanup the issues until we can determine what in
mlir/stablehlo is the source of the issue.
See the related issues here:
[SHARK-Turbine#556](https://github.com/nod-ai/SHARK-Turbine/issues/556)
1. Adds uint8 casting to onnx.Cast op
2. Fixes an issue with onnx.DequantizeLinear when the scale comes with
shape [1].
3. Adds support for unsigned types in an AtenItemOp folder
4. Adds a simpler quantized model for easier debugging
5. Adds a fusion pass to convert [quant -> dequant -> transpose -> mm]
patterns to [transpose -> quant -> mm].
6. Moved some xfails that are still not passing, but for different
reasons than onnx.cast failures.
This was found while tracing backwards graphs: the convolution_backwards
op will return None if the first result is not needed. Confirmed by
defining a custom op with a `Tensor` return signature and having its
meta kernel return None.
Two e2e tests (AdaptiveAveragePool1/2dUnitOutputSizeDynamic) were
failing due to numerics. This was as a result of passing -1 as the
kernel size in the lowering for the corresponding onnx op
GlobalAveragePool.
Reshaping tensors depend on directly matching individual dimensions to
their corresponding dim in the `torch.view` reshape dimensions. This
involves decoupling dynamic dimensions from their static counterparts
and support cleanup / canonicalization.
This commit adds the OnnxToTorch lowering for the Mish, Softplus,
HardSwish, Trilu, ThresholdedRelu op
Signed-Off By: Vivek Khandelwal <vivekkhandelwal1424@gmail.com>
The previous conversions for AtenAdaptiveAvgPool1dOp and
AtenAdaptiveMaxPool2dOp are refactored into a general templated
conversion that works for all of the AtenAdaptive...PoolNdOp's.
New support is added for the following ops:
1. AtenAdaptiveMaxPool1d
2. AtenAdaptiveMaxPool3d
3. AtenAdaptiveAvgPool3d
Support is also provided for passing inputs without batch dimensions.
For example, applying adaptive_avg_pool2d to an input tensor of rank 3.
After [pytorch #118162](https://github.com/pytorch/pytorch/pull/118162)
gets down to torch-mlir, I'll add a test for AdaptiveMaxPool1d with
return_indices (which will pass with that upstream fix).
---------
Co-authored-by: James Newling <james.newling@gmail.com>
This adds support for converting DynamicQuantizeLinear from torch-onnx
to torch.
I could not get an e2e test to pass, since there seems to be some issues
with uint8 casting somewhere lower in the pipeline. For example
compiling with IREE for llvm-cpu, I would get either the correct zero
point (if zp < 128) or the correct zero-point minus 256 (if zp >= 128).
The output tensor seems to always return a tensor of zeros, which also
occurs when running uint8 examples through QuantizeLinear.
Edit: the first problem can be resolved by casting the output back to
uint8 on output, the second problem is resolved with PR #3018
Added support for dynamic shapes in `flattenusingints` op in tosa
dialect. Due to this some Argmax tests pass
This PR fixes this issue https://github.com/llvm/torch-mlir/issues/3004
The following tests pass after this PR
```
1. "ArgmaxIntModule_basic"
2. "ArgmaxIntModule_multiple_maxs"
3. "ArgmaxModule_basic"
```
Reduce mean lowerings did not succesfully lower to `linalg` via torched.
There were two separate paths that could be consolidated to a single
simpler pass. This resulted in a significant improvement in test
coverage.
If the broadcast shape is length-1 at a dim while `?` in the input dim
then we need to broadcast to the dynamic dim. This is equivalent to
taking a max of two dimensions.
This folds small version of the tensor-scalar comparison operators as
they are commonly used for shape computations. This includes le, lt, ge,
gt, eq, and ne.
The current padding operation was not functional for dynamic shapes.
Updated and enabled tests so that onnx.pad tests pass.
Work TBD for reflection padding.
Set PyTorch and TorchVision version to nightly release 2024-03-07.
This commit also removes the deprecated constraints API:
342e7929b8
Signed-Off By: Vivek Khandelwal <vivekkhandelwal1424@gmail.com>
This mostly copy-pastes the reduce minimum implementation to reduce max
to improve test coverage. We also improve the aten lowering for min/max
dim for unsigned types.
The addition of an e2e test is actually provided in the Shark-Testsuite.
This adds 2 test cases for the gridsampler e2e test.
Also as intended there were some items found which needed correction, so
the Gridsampler op has also a change.
Current implementation depends on using `aten.view` which has issues
inferring tensor collapse/expand operations during the lowering to
`linalg`. Using flatten and unsqueeze better infers what the later
reshape behavior.
Add e2d support for `aten.linalg_norm` by decompose it to
`aten.linalg_vector_norm`.
Lowering to `aten.linalg_matrix_norm` is still unsupported.
To Test:
`python -m e2e_testing.main -v`
---------
Co-authored-by: Ze Zhang <ze.zhang@getcruise.com>
Existing lowering via aten.view does not work as well for dynamic shapes
as the lowering to tensor.expand must re-infer dynamic shape matching.
Better to directly lower.
A bunch of small fixes are interlinked and trigger crashes if not
addressed as a group. This includes:
- aten view when expand from a rank-0 tensor
- slice folder with negative indices
- `aten._shape_as_tensor` folder on a rank-0 tensor
- `aten.cat` of a tensor with a length-0 tensor
The corrective transpose at the end is computed incorrectly. Is it
actually computin the inverse transpose. Inverting the permutations
fixes the issue.
Torch lowering only supported the most recent version. Refactored the
lowering so more easily handle default values and optional operands /
attributes.
Added Support for float dtype in in torch.arange in TOSA Dialect
This resolves the following issue :-
https://github.com/llvm/torch-mlir/issues/2762
The following test cases are passing after this change
1. ArangeDtypeIntModule_basic
2. ArangeFloatModule_basic
3. ArangeNegativeStartFloatModule_basic
4. ArangeStartFloatModule_basic
5. ArangeStartNegativeStepFloatModule_basic
6. ArangeStartOutDtypeModule_basic
7. ArangeStartStepFloatModule_basic
---------
Co-authored-by: James Newling <james.newling@gmail.com>
We collapsed and broadcasted scatter indices to a single element
version. We should instead upport `tm_tensor.scatter`s support for
multiple indices and the implicitly broadcasted behavior. This avoids
the serialization and materializing a needlessly large indices tensor.
There is no reason to treat `ConstantOfShape` as a specialized import
any as there exists a onnx-to-torch equivalent. Dropping the import
coding and adding support for resource conversion substantially
increases test coverage for dynamically shaped tests.
Strided slicing can occur with a negative stride. In these cases we need
to bound end differently. This included removing a function that was
generating bad limits.
Simple folder for limited size aten tensor operations. This is primarily
useful for shape computation folding as they unfortunately can use
`aten` operators. Add, sub, mul are common examples of these folders.
Onnx slice lowering used arange needlessly instead of directly
constructing the constant dimension values. This makes lowerings to
linalg struggle as multiple folders are required to get what is a
constant index value.
Even though the reference compiler is not about performance, inlining
the generated sparse helper methods has a rather big positive impact on
performance, leaving a much better first impression. Therefore, we added
this inlining pass (which leaves all other PyTorch modules unaffected,
since they tend to be one big main() method to start with).
testing:
$./tools/e2e_test.sh --config linalg
Summary:
Passed: 1164
Expectedly Failed: 8
$ python -m e2e_testing.main --config=torchdynamo
Summary:
Passed: 976
Expectedly Failed: 162
We can route the torch tests via `onnx` using the `torch.onnx.export`
tooling. We can then reimport, lower to torch, and compile to linalg to
validate the onnx path is working correctly.
The current implementation exposes some failures in the `onnx` path so
we cannot enable the onnx test suite yet due to segmentation faults.
This commit adds the OnnxToTorch lowering for cosh, acosh, asin, asinh,
and atanh op.
This commit also adds the TorchToLinalg lowering for acosh, asin, asinh,
and atanh op.
Signed-Off By: Vivek Khandelwal <vivekkhandelwal1424@gmail.com>
Some operations include a backend matcher for specialized operations. We
map these back to generics so they appropriately match to the high
performance versions. This is done for the attention operation.
This patch makes the Protobuf package mandatory in addition to forcing a
config mode search. The (default) module mode search looks for the
CMake-provided FindProtobuf.cmake file, but this file does not list
Abseil as a dependency, causing linker issues like the one below:
```
ld: Undefined symbols:
absl::lts_20230802::log_internal::LogMessageFatal::LogMessageFatal(char const*, int, std::__1::basic_string_view<char, std::__1::char_traits<char>>), referenced from:
google::protobuf::RepeatedPtrField<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>>::TypeHandler::Type const& google::protobuf::internal::RepeatedPtrFieldBase::Get<google::protobuf::RepeatedPtrField<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>>::TypeHandler>(int) const (.cold.1) in OnnxImporter.cpp.o
```
By forcing a config mode search, CMake looks for the file that is
installed as part of the protobuf package and which does contain the
Abseil dependency. This workaround is also mentioned in a GitHub issue
for Protobuf:
https://github.com/protocolbuffers/protobuf/issues/12292#issuecomment-1529680040.
This PR introduces a sparse_jit wrapper that can run simple models with
sparse tensor inputs end-to-end. The implementation shows all required
components on modifying sparse tensor types with a 1:N relation on the
call sites. Two tests shows that the JIT runs end-to-end while computing
the correct results.
More details to follow (generalizing to COO and different ranks, as well
as support for *output* sparse tensors), but the general concepts are
all here now.
**_Update: Thanks to Rob, bump to proper LLVM/MLIR hash is done!_**
_**NOTE that all parameter passing changes are nicely done "downstream"
in MLIR, so very little changes are required in torch-mlir code
proper**_
---------
Co-authored-by: Franz Haniel <77495327+frafranz@users.noreply.github.com>
Co-authored-by: Franz Haniel <franz.haniel@amd.com>
The lowering decomposes AtenTraceOp into an AtenDiagonalOp followed by
AtenSumOp.
The progress is tracked in
https://github.com/nod-ai/SHARK-Turbine/issues/333.
---------
Co-authored-by: Franz Haniel <franz.haniel@amd.com>
There is no lowering support for math::AbsIOp, so if the operand is an
integer type, it will fail to lower to math::AbsFOp since the op operand
#0 must be floating-point-like.
This adds a few passes that will ensure linalg with sparse tensors are
properly lowered to loops and can run using the ExecutionEngine for
testing (a few details on parameter passing from PyTorch still TBD)
Test results:
$ ./tools/e2e_test.sh --config linalg
Summary:
Passed: 1144
Expectedly Failed: 8
$ python -m e2e_testing.main --config=torchdynamo -v
Summary:
Passed: 960
Expectedly Failed: 163
Filed issue:
https://github.com/pytorch/pytorch/issues/119407
Folds aten::index_select ops under the following conditions:
1. If the input and output are the same shape, the indexing operation is
a NOP, so just return the input.
2. If the input has shape <1x1x...xNx...x1> (all 1's except for one
dim), and the output shape is <1x1x...x1> (all 1's), then there is a
single index, so extract the single element value and return a tensor
with that value.
---------
Co-authored-by: Dave Liddell <dliddell@xilinx.com>
Lowering of torch.aten.all.dim to linalg.
Per PyTorch documentation:
> This function matches the behaviour of NumPy in returning output of
dtype bool for all supported dtypes except uint8. For uint8 the dtype of
output is uint8 itself.
Since there is no support for ui8 in torch-mlir currently
(https://github.com/llvm/torch-mlir/pull/1384#issuecomment-1260011334)
implementation returns failure for that case.
Link to related RFC:
https://discourse.llvm.org/t/rfc-rename-torch-mlir-compile-apis-and-introduce-fx-based-analogs/76646
This commit updates the documentation, tests, CMake files, and API for
the proposed changes in the RFC. There is a new torch_mlir/fx.py for
user level APIs related to importing modules and a corresponding test
for this path can be found at test/python/fx_importer/basic_test.py.
---------
Co-authored-by: MaheshRavishankar <mravisha@amd.com>
If a tensor is initialized by a list with a single constant integer,
this folder turns it into a torch.vtensor.literal
---------
Co-authored-by: Dave Liddell <dliddell@xilinx.com>
So that the CumSum Op in OPT can get the constant that it requires to be lowered to TMTensor
---------
Co-authored-by: Rob Suderman <rob.suderman@gmail.com>
Co-authored-by: Xida Ren <xida.ren.dev@gmail.com>
We do not support average pool when `countIncludePad is set to false.
However if the input is unpadded then the setting of the boolean is
unneeded. Extended use by checking if padding is zero before rejecting
the lowering.
Required some massaging of LTC to make it warning clean, and I had to
manually disable some warnings on the generated source files (which we
don't control).
The project is warning clean now.
The `-Werror` flag is disabled by default as we can't control everywhere
people will try to build/install. The CI enables it via
-DTORCH_MLIR_ENABLE_WERROR_FLAG=ON.
Linalg has quantized specific operations. We can lower to these
operations when there is a known zeropoint and scale operations. This
allows the `convolution` to occur with lower bitwidth's, improving the
overall performance.
After noticing a number of commits with unrelated formatting changes,
I think something was changed with clang-format at one point and we're
seeing a number of unrelated changes. Doing a refresh can help avoid
this.
The changes made here came from
```
find lib -iname *.h -o -iname *.cpp | xargs clang-format -i --style=llvm
find include -iname *.h -o -iname *.cpp | xargs clang-format -i --style=llvm
find projects -iname *.h -o -iname *.cpp | xargs clang-format -i --style=llvm
```
Per the RFC and numerous conversations on Discord, this rebuilds the
torch-mlir CI and discontinues the infra and coupling to the binary
releases
(https://discourse.llvm.org/t/rfc-discontinuing-pytorch-1-binary-releases/76371).
I iterated on this to get latency back to about what it was with the old
(much larger and non-ephemeral) runners: About 4m - 4.5m for an
incremental change.
Behind the scenes changes:
* Uses a new runner pool operated by AMD. It is currently set to manual
scaling and has two runners (32-core, 64GiB RAM) while we get some
traction. We can either fiddle with some auto-scaling or use a schedule
to give it an increase during certain high traffic hours.
* Builds are now completely isolated and cannot have run-to-run
interference like we were getting before (i.e. lock file/permissions
stuff).
* The GHA runner is installed directly into a manylinux 2.28 container
with upgraded dev tools. This eliminates the need to do sub-invocations
of docker on Linux in order to run on the same OS that is used to build
wheels.
* While not using it now, this setup was cloned from another project
that posts the built artifacts to the job and fans out testing. Might be
useful here later.
* Uses a special git cache that lets us have ephemeral runners and still
check out the repo and deps (incl. llvm) in ~13s.
* Running in an Azure VM Scale Set.
In-repo changes:
* Disables (but does not yet delete):
* Old buildAndTest.yml jobs
* releaseSnapshotPackage.yml
* Adds a new `ci.yml` pipeline and scripts the steps in `build_tools/ci`
(by decomposing the existing `build_linux_packages.sh` for in-tree
builds and modularizing it a bit better).
* Test framework changes:
* Adds a `TORCH_MLIR_TEST_CONCURRENCY` env var that can be used to bound
the multiprocess concurrency. Ended up not using this in the final
version but is useful to have as a knob.
* Changes the default concurrency to `nproc * 0.8 + 1` vs `nproc * 1.1`.
We're running on systems with significantly less virtual memory and I
did a bit of fiddling to find a good tradeoff.
* Changed multiprocess mode to spawn instead of fork. Otherwise, I was
getting instability (as discussed on discord).
* Added MLIR configuration to disable multithreaded contexts globally
for the project. Constantly spawning `nproc * nproc` threads (more than
that actually) was OOM'ing.
* Added a test timeout of 5 minutes. If a multiprocess worker crashes,
the framework can get wedged indefinitely (and then will just be reaped
after multiple hours). We should fix this, but this at least keeps the
CI pool from wedging with stuck jobs.
Functional changes needing followup:
* No matter what I did, I couldn't get the LTC tests to work, and I'm
not 100% sure they were being run in the old setup as the scripts were a
bit twisty. I disabled them and left a comment.
* Dropped out-of-tree build variants. These were not providing much
signal and increase CI needs by 50%.
* Dropped MacOS and Windows builds. Now that we are "just a library" and
not building releases, there is less pressure to test these commit by
commit. Further, since we bump torch-mlir to known good commits on these
platforms, it has been a long time since either of these jobs have
provided much signal (and they take ~an hour+ to run). We can add them
back later post-submit if ever needed.
This includes custom op matching for decomposed operations and fusing
dequantization into dense operations. As a validation we compare
to the dequant+mm torch implementation.
The logic here is very similar to the conversion for AdaptiveAvgPool1d
#2661 with a few modifications:
1. buffVal = -inf instead of 0
2. the main linalg generic op accumulates a max, instead of a sum, to
the first output tensor
3. avg pooling requires dividing the sum pool by the kernel width, which
we stored as an auxilliary tensor (kSizeTensor). Here, the auxiliary
tensor will be recording the indices. Strangely enough, the only
signature available for this function is to return indices, and it
appears that they must be computed whether the user desires them or not.
See
[pytorch/torch/nn/functional.py](https://github.com/pytorch/pytorch/blob/main/torch/nn/functional.py#L1174).
Before writing other adaptive pooling conversions, the logic of this
decomposition should be rolled into a helper function that will work for
both max and avg pooling ops. Even the auxiliary tensor should likely be
automated. This code was written in a slightly more tedious way than
strictly necessary (often using loops to fill SmallVectors up to rank-2,
which is only two in this case), in order to more easily facilitate the
transition to a helper function.
convolution with [time,batch,channel] ordering, as opposed to the
default [batch, channel, time]. Currently implementing by transposing
the input and output, but may need to get its own implementation in the
future because this is supposed to be an op that gives a speedup. This
is used by fairseq
(https://github.com/facebookresearch/fairseq/issues/172).
(in case you were wondering like me, this is different from transposed
convolution. Transposed convolution has fractional strides).
---------
Co-authored-by: Xida Ren <xida.ren.dev@gmail.com>
Co-authored-by: Frederik Harwath <frederik.harwath@amd.com>
Handle both `torch.dequantize` and `torch.quantize_per_tensor` including
the op based quantization parameter tracking. This includes adding
`qint32` to torch types as it was missing during the initial type
inclusion.
For testing we only have `torch.int8` and `torch.float` types on
function boundaries as the `qint8` types require passing the scale
and zero point quantization information which is not supported yet.
This PR updates the torch-to-tosa conversion with following changes:
- Support torch.none as min/max input argument for tosa.clamp op
- Support negative value as start index for tosa.slice op
- Add tosa.logical_or lowering support
e2e test:
python -m e2e_testing.main --config=tosa
LIT tests:
cmake --build build --target tools/torch-mlir/all
---------
Co-authored-by: Ze Zhang <ze.zhang@getcruise.com>
penguin_wwy
Xinyu Yang
zjgarvey
Vinayak Dev
IanWood1
Aart Bik
Xinan Jiang(姜曦楠)
Rob Suderman
Yuanqiang Liu
Jae Hoon (Antonio) Kim
Xida Ren (Cedar)
Vivek Khandelwal
ptrifunovic98
Stella Laurenzo
schnkmwt
Xida Ren (Cedar)
Abhishek-TyRnT
Pavani Chowdary
Devjiu
Andreas Falkenberg
Scott Todd
Ze Zhang
Chi_Liu
mmakevic
Aart Bik
aldesilv
Ashay Rane
Franz Haniel
Avinash Sharma
Dave Liddell
saienduri
Ilija Kalinić
James Newling
Quinn Dawkins
John Wu
Sungsoon Cho
lonely eagle
lisaliu1
Frederik Harwath