Changes made during upstreaming:
* Removed comments attributing some copied code back to torch-mlir
(since it is now repatriated).
* Re-organized imports.
* Inlined RefMapping/RefTracker and TypeSubclassMap from an external
utility module.
* Added FxImporter class comments.
* Updated stack trace extraction to be fail safe.
* Added an entry-point for `import_frozen_exported_program` which uses
the shiny new upstream `torch.export.export()` API (versus the
lower-level/older API that Turbine is presently using). This
necessitated a small FX rewrite to line external state management up
with current conventions.
* Adapted one of Turbine's importer tests to go with this initial
submission. Turbine unfortunately has a lot of more-integration-ey
tests, and I would like to extract those as more of unit tests of the
importer features and upstream them that way vs trying to copy directly.
For now, one overall test with the initial submission gets us moving.
I acknowledge that there are some code quality things that could be
improved in this submission: this was authored over the course of many
months (and often via some trial and error). I would like to keep it
relatively converged with the downstream for the next few steps while
getting the test suite upstreamed. And then it will be easier to take a
hygienic pass through the code.
Including co-authors for contributors in the git log of the original
repository.
Co-authored-by: Ean Garvey <87458719+monorimet@users.noreply.github.com>
Co-authored-by: Avinash Sharma <aviator1994@gmail.com>
Co-authored-by: Arham Khan <arhammkhan@gmail.com>
Co-authored-by: brucekimrokcmu <kwangkyk@alumni.cmu.edu>
Co-authored-by: saienduri <77521230+saienduri@users.noreply.github.com>
The expression for HardSigmoid in Onnx
(https://onnx.ai/onnx/operators/onnx__HardSigmoid.html): max(0, min(1,
alpha * x + beta))
is inherently different from HardSigmoid in Torch
(https://pytorch.org/docs/stable/generated/torch.nn.Hardsigmoid.html)
which is: if x < -3 -> 0
elif x > 3 -> 1
else x/6 + 1/2
That being said, it was just better to compute out the entire expression
when translating the Onnx expression to Torch mlir, which is done in
this PR. Some of the logic is shared from the files in
`DecomposeComplexOps`. Therefore, refactored some shared logic between
`DecomposeComplexOps` and `DefaultDomainGToP` and put it in a `Utils`
file.
This PR adds the `enable_ir_printing` option to `torch_mlir.compile`,
which can be used to print the IR for all intermediate passes.
When running the added test file via:
```shell
$ python test/python/compile.py 2> tiny.stderr
```
the file `tiny.stderr` is about 700 KB.
The three remaining compare operations
onnx.Greater
onnx.Less
onnx.GreaterOrEqual
Are also added with this push request.
This concludes a set of basic tensor compare functions.
Lowerings for `transpose` from ONNX to `aten`. Implementation depends on
making multiple `aten.transpose` operations swapping pairs of dimensions.
As `onnx.transpose` can swap around any dimensions it may require
constructing multiple `aten.transpose`.
This replaces the lowering of aten.cat with tensor.concat, allowing more
efficient handling of concatenations in downstream flows. The refbackend
populates concat decomposition patterns that can be used to recover the
previous lowering.
This commit adds the OnnxToTorch support for Reciprocal, Round,
ScatterElements, Sigmoid, Sin, Tanh, Sqrt, Sub, Sum, Where, Xor,
Squeeze, Unsqueeze ops.
For reviewers, the ops that weren't trivial and probably require extra
review are Sum, Squeeze, and Unsqueeze.
Lowerings for `selu` lowerings for ONNX to the corresponding torch
implementations. Torch's `selu` implementation has fewer features so
we use the a generalized `elu` with the input scale set to `1.0`.
Simple Python console script to import an ONNX protobuf to the torch
dialect for additional processing.
For installed wheels, this can be used with something like:
```
torch-mlir-import-onnx test/python/onnx_importer/LeakyReLU.onnx
```
Or from a dev setup:
```
python -m torch_mlir.tools.import_onnx ...
```
This is part 1 of 2, which will also include upstreaming the FX
importer. I started with ONNX because it forces some project layout
updates and is more self contained/easier as a first step.
Deviating somewhat from the RFCs on project layout, I made the following
decisions:
* Locating the `onnx_importer.py` into `torch_mlir.extras` as Maks
already has opened up that namespace and it seemed to fit. Better to
have fewer things at that level.
* Setup the build so that the root project only contains MLIR Python and
pure Python deps (like the importers), but this can be augmented with
the `projects/` adding more depending on which features are enabled.
* The default build continues to build everything whereas in
`TORCH_MLIR_ENABLE_ONLY_MLIR_PYTHON_BINDINGS=1` mode, it builds a
`torch-mlir-core` wheel with the pure contents only.
`onnx_importer.py` and `importer_smoke_test.py` are almost verbatim
copies from SHARK-Turbine. I made some minor local alterations to adapt
to paths and generalize the way they interact with the outer project. I
expect I can copy these back to Turbine verbatim from here. I also
updated the license boilerplate (they have the same license but slightly
different project norms for the headers) but retained the correct
copyright.
Other updates:
* Added the ONNX importer unit test (which also can generate test data)
in lit, conditioned on the availability of the Python `onnx` package. In
a followup once I know everything is stable, I'll add another env var
that the CI can set to always enable this so we know conclusively if
tests pass.
* Moved the ONNX conversion readme to `docs/`.
* Renamed CMake option `TORCH_MLIR_ENABLE_ONLY_MLIR_PYTHON_BINDINGS` ->
`TORCH_MLIR_ENABLE_PYTORCH_EXTENSIONS` and inverted the sense. Made the
JitIR importer and LTC options `cmake_dependent_options` for robustness.
This commit adds the OnnxToTorch support for BitwiseXor, BitwiseOr, Div, Equal, Cast,
Ceil, Floor, Cos, and Clip op.
This commit also adds the TorchToLinalg support for aten.clamp.Tensor and aten.clamp_min.Tensor op.
Signed-Off By: vivekkhandelwal1424@gmail.com
Despite aten.mm requiring the input and output types match, we still opt
to maintain signedness semantics in case later passes try to do any sort
of integer type narrowing.
This commit adds the OnnxToTorch support for Atan, Bitshift, BitwiseAnd,
and BitwiseNot op.
This commit also adds the TorchToLinalg support for AtenBitwiseLeftShiftTensorOp.
Signed-Off By: vivekkhandelwal@nod-labs.com
Adds a pipeline to convert custom ops and metadata represented as
`torch.operator` custom ops to corresponding `torch` ops where possible.
This is part of a multi-part approach for building ONNX import in as a
regular feature of torch-mlir. It is focused on the conversions vs the
infra. We will end up maintaining a [pure-python
importer](https://github.com/nod-ai/SHARK-Turbine/blob/main/python/shark_turbine/importers/onnx_importer.py)
to go with this in torch-mlir, and we will also maintain test case
generation utilities derived from it.
I have left substantial documentation in the README of the conversion
directory, including the recommended approach that we will take to keep
building this out.
(note that this organizes the code to coincide with the refactoring in
#2442 versus the current flat arrangement)
The logic for lowering the aten view op to linalg is fairly complex.
In this PR I have tried to follow all non-failing paths through the
lowering and add unit tests where they're missing.
There is 1 logical change to the lowering: redundant tensor.cast ops
(same source and destination type) are folded.
This lifts the core of the jit_ir_importer and ltc out of the pt1
project, making them peers to it. As a side-effect of this layering, now
the "MLIR bits" (dialects, etc) are not commingled with the various
parts of the pt1 project, allowing pt1 and ltc to overlay cleanly onto a
more fundamental "just MLIR" Python core. Prior to this, the Python
namespace was polluted to the point that this could not happen.
That "just MLIR" Python core will be introduced in a followup, which
will create the space to upstream the FX and ONNX pure Python importers.
This primary non-NFC change to the API is:
* `torch_mlir.dialects.torch.importer.jit_ir` ->
`torch_mlir.jit_ir_importer`.
The rest is source code layering so that we can make the pt1 project
optional without losing the other features.
Progress on #2546.
- adds support for an optional verifier to the generated torch op
tablegen (GeneratedTorchOps.td)
- uses the above to add a verifier for the torch permute op.
Motivation: I hit an unclear error from linalg while developing a
decomposition pass for pixel_shuffle. The error would have been clearer
if the problem had been detected earlier in the invalid aten.permute op.
Testing: new tests added. To run added tests, from the base directory
run
```
./build/bin/llvm-lit test/Dialect/Torch/invalid.mlir
```
This is a first step towards the structure we discussed here:
https://gist.github.com/stellaraccident/931b068aaf7fa56f34069426740ebf20
There are two primary goals:
1. Separate the core project (C++ dialects and conversions) from the
hard PyTorch dependencies. We move all such things into projects/pt1 as
a starting point since they are presently entangled with PT1-era APIs.
Additional work can be done to disentangle components from that
(specifically LTC is identified as likely ultimately living in a
`projects/ltc`).
2. Create space for native PyTorch2 Dynamo-based infra to be upstreamed
without needing to co-exist with the original TorchScript path.
Very little changes in this path with respect to build layering or
options. These can be updated in a followup without commingling
directory structure changes.
This also takes steps toward a couple of other layering enhancements:
* Removes the llvm-external-projects/torch-mlir-dialects sub-project,
collapsing it into the main tree.
* Audits and fixes up the core C++ build to account for issues found
while moving things. This is just an opportunistic pass through but
roughly ~halves the number of build actions for the project from the
high 4000's to the low 2000's.
It deviates from the discussed plan by having a `projects/` tree instead
of `compat/`. As I was thinking about it, this will better accommodate
the follow-on code movement.
Once things are roughly in place and the CI passing, followups will
focus on more in-situ fixes and cleanups.
NonValueSemantic Ops like Add_, div_, etc. expect result DType to be the
same as the first input. However, current implementation would result in
wrong result type for case like:
```python
a = torch.randn(3, 3).half() # float16
b = torch.randn(3, 3) # float32
a += b # i.e. torch.ops.aten.add_(a, b)
```
torch expects `a` to be float16, but dtype refinement would infer
float32 type, since it's replaced by `aten.add`.
Add aten.isclose op
Add its torch-to-tosa lowering
Update the TorchToTosa/basic.mlir tests
To test e2e tosa lowering:
`python -m e2e_testing.main -v -c=tosa`
---------
Co-authored-by: Ze Zhang <ze.zhang@getcruise.com>
Add aten.unflatten.int op
Add its torch-to-tosa lowering
Update the TorchToTosa/basic.mlir tests
To test e2e tosa lowering:
`python -m e2e_testing.main -v -c=tosa`
---------
Co-authored-by: Ze Zhang <ze.zhang@getcruise.com>
Strict symbolic shapes allow us to assume numpy-style dynamic broadcasts
never occur. This allows us to strengthen the folder for broadcasts to
cases where the rank is the same and all shapes match (including dynamic
sentinel values).
When importing dynamic shaped programs from Dynamo, via torch.compile or
torch.export, we can assume that strict symbolic shape checks have been
done prior to generating torch IR. Among other shape checking, this
eliminates the case where an unknown dimension can be dynamically '1' in
a way that signals a broadcast.
Adds a `isAssumingStrictSymbolicShapes` utility which consults a
`torch.assume_strict_symbolic_shapes` attribute on an enclosing scope
and returns true if present.
In the linalg pipeline, many runtime checks are elided when this returns
true.
Corresponding commits:
* mlir-hlo: 16886a108eff5197f816ca0f1950cc5ff1b078d9
* stablehlo: 77a59815a82b34f7b08ed2d42a711d9920682d0e
* llvm-project: 4acc3ffbb0af5631bc7916aeff3570f448899647
* Adapt to ByteCodeOpInterface changes.
* Adapt to RegionBranchPoint changes: https://reviews.llvm.org/D159116
* Adapt inferReturnTypes to get the value from properties.
* Adapt invalid.mlir to properties syntax
* [TOSA] Align with custom assembly format change.
* [TOSA] handle change of axis to int32 type
* [TOSA] Restore improper convert to i32
Landing with Windows broken (it cannot be fixed because of the way the mlir-hlo dep is inserted). Will followup with an untangling.
---------
Co-authored-by: TatWai Chong <tatwai.chong@arm.com>
Co-authored-by: Eric Kunze <eric.kunze@arm.com>
* view_as_real test case, allow dtype in testutils.randn
* abstract python upstream func implemented
* fixed upstream dtype func, implemented view_as_real backend op
* formatted AtenViewAsRealOp, removed change in e2etest/framework
* removed test suit from reshape_like.py, because it's moved to basic.py
* implemented C-API wrapper for mlirComplexF128 type
* fixed torch.complex dtype width in MLIR and Torch MLIR, deleted float16 dtype dict
* Changed IR input of aten fft_fft unit test
* code refactored
* code refactored and fixed ci test
* refactored: removed white spaces, and rolled back to having both input/output affine expr
* refactored: deleted output affine expr to reduce redundancy
* xfail ltc backend
* removed ComplexImag and ComplexReal from torchdynamo xfail set
* copied and pasted from main branch as there's no change to be made in this file
* refactored abstract_interp_lib_gen.py
* refactored: torchtypes.td, formatted, removed commented out code
* Support brevitas custom op (#2320)
* f16 change for brevitas
* Adapt the change of brevitas quant custom op name
* Add unit tests
* Make brevitas conversions isolated
* Address the comments
---------
Co-authored-by: dan <danimal197@gmail.com>
When using custom ops, sometimes PyTorch will insert namespaces to the
abstract interpretation function name in the format:
`__torch__.{namespace_1}.{namespace_2}...{op_name}`. The extra
namespaces are not part of the abstract interpretation function name,
so it needs to be removed before generating the library of MLIR
snippets of abstract interpretation functions. This commit adds
support for removing the namespace information.
* LTC->MLIR Debug Info support
* SW-95317 Propagate Lazy->Jit->MLIR scope name.
* Enhance location information based on op names
Currently, the location information attached to the ops just considers
the filename, line number and column number. Attaching operation name
would help identify the type of computation by just looking at the
profile of execution.
* Update locations logic; updated debug-info.py test
* Use {scope}/{op_name} format to track names by default
---------
Co-authored-by: Gleb Kazantaev <gleb.kazantaev@cerebras.net>
Co-authored-by: Mark Browning <mark@cerebras.net>
Co-authored-by: Vimal Patel <vimal@polymagelabs.com>
The implementation at this place was a remnent of the times the pipeline was
run only once.
Rely instead on the backend verification, after optimizations have had an
opportunity to resolve some uncertainties. (e.g. `!torch.optional`).
* RecomposeComplexOps: Remove dead slice op
* lib/Dialect/Torch/IR/TorchOps.cpp: Fold slice ops even when they are on non-value tensors
* lib/Conversion/TorchToTosa/TorchToTosa.cpp: Fix slice start/end out of range/none
* lib/Dialect/Torch/IR/TorchOps.cpp: AtenSliceTensorOp::fold: Fold slices that go from 0:int_max
* More tests for aten.split.Tensor
In PyTorch, the `NumberType` is equal to `Union[int, float,
complex]`. However, the abstract interpretation library was treating
the `NumberType` as `Union[int, float]`, resulting in type mismatches
when reifying certain dtype functions. This commit fixes the type
inconsistency by having the abstract interpretation functions take as
an input a `Union[int, float, complex]` for the ops that take
`!torch.number` inputs.
This commit adds the support for index.Tensor op when the index values
are negative. This commit wraps around the index values by checking
their values at run time.
Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
check the return type of the division to figure out whether to use
the floating point implementation of a division or to use the integer.
the issue rose from the fact that the inputs are all integer but the
result was casted to floating point. The conversion then chose to
use the integer implementation of division which is not legal in tosa
when all the inputs get casted to floating point.
fix(TorchToLinalg): AtenDivScalarOp
upcast self operand as well if applicable, the self operand must also
be casted to float as it can be an integer.
When `use_tracing=True` is used to import a model into Torch-MLIR,
several casts get inserted in the IR to bridge the untyped inputs and
outputs with the typed body of the computation. These casts create
extra aliases of tensors that cause the current analysis in
`maximize-value-semantics` to fail.
In particular, the `maximize-value-semantics` analysis assumes that the
only valid alias right after an overwrite is the overwritten
alias. So, if there is a use of a casted version of the overwritten
alias after the overwrite, the analysis fails.
This commit improves the analysis by identifying all cast-like aliases
of the overwritten alias and allowing such aliases to be used after an
overwrite.
Because this issue only arises when using tracing, it cannot be
currently tested e2e, so only lit test is added.
Lowering torch operations that allow different compatible data types
in its operands to tosa end up generating invalid tosa IR with mixed
data types. In tosa spec, certain operations (generally element-wise
operations) require all operands to have the same data type.
Add wrapper functions for those element-wise tosa ops to perform op
creation with type conversion if necessary.
This commit adds dtype functions for all the torch ops that did not
previously have one and removes the pass `RefineTypes`, since the
abstract interpretation library now takes care of all the dtype
propagation.
All dtype functions added are tested except for
- `aten.embedding`
- `aten._embedding_bag`
- `aten.embedding_bag`
These functions need a change to the testing framework to allow
specifying the actual data inside the tensor used for testing. I will
fix this in a follow up patch.
Co-authored-by: Jiahao Li <liplus17@163.com>
Bool tensors are represented in TorchScript as an array of
`int8_t`s. However, when importing them into Torch-MLIR, the importer
was assuming the array had `int32_t` elements, leading to the importer
reading into memory that was out of bounds. This commit fixes the
casting of the bool tensor.
This commits adds the support for cases for index_put_op:
1.) where index is a 2-d tensor.
2.) where indices is a list of tensors and none, with exactly
2 non none tensors along the consecutive dimensions.
This commit also adds a utility to compute the broadcast shape
given the two input tensors.
Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
This commit adds the ability to specify extra abstract interpretation
functions in `torch_mlir.compile` to use during type refinement. This
allows users to easily add custom ops without having to interact with
MLIR or C++ directly.
To keep things simple in shape functions, `Scalar` inputs are
considered `float`s. This means that when inserting the shape
functions into the IR, we must cast any `!torch.number`s into `float`s
so that the operand type matches the expected type in the shape
function. This commit adds the cast from `Scalar` to `float`.
The original design for the dtype functions outlined in
https://github.com/llvm/torch-mlir/issues/1462 was unable to properly
handle ops that take optional tensors as an input when the optional
tensor has a value of None. By the time the op gets imported into
torch-mlir, if an optional value is None, all information about the
original type is lost from the op type signature, preventing
torch-mlir from knowing if a value of None was from an optional tensor
or not, which was crucial in the original design since each tensor
argument must be turned into two separate arguments for the dtype
function.
This commit changes the interface to dtype functions such that each
tensor turns into a tuple of two ints, the first representing the rank
of the tensor and the second the dtype of the tensor. Since now there
is a one-to-one correspondence between the operands of an op and the
operands of its dtype function, there is no ambiguity about which
operand of the op corresponds with which operand of the dtype
function.
To test the implementation, this commit defines dtype function for
convolution op, which takes one optional tensor as an argument.
* LowerToBackendContract: Explicitly error out on unimplemented operator
But only reject torch.operator when results are invalid.
Otherwise it might be a custom op that the backend supports.
Currently, the op `torch.tensor_static_info_cast` will not get
canonicalized away if the result type has any shape or dtype
information. This is because `isValidSubtype` only returns true when
the tensor types being compared are exactly the same or the supertype
has no shape and dtype information. Being unable to canonicalize away
the `torch.tensor_static_info_cast` gets in the way of further
optimizations, such as shape propagation.
This commit improves `isValidSubtype` by adding logic that compares
the shapes and dtypes of the two tensor types to determine of one type
is indeed a valid subtype of the other.
Fixes https://github.com/llvm/torch-mlir/issues/1926
The data-flow analysis does not always propagate information to the
entire graph. This results in some lattice elements being
uninitialized. Currently the lattice elements are not checked to see
if they are uninitialized before rewriting the graph, potentially
resulting in invalid IR (see
https://github.com/llvm/torch-mlir/issues/1896).
This commit adds handling for uninitialized lattice elements.
This patch replaces all MHLO operations with their StableHLO
counterparts and adds a validation pass to ensure that no MHLO operations
remain before translating all Stablehlo operations to the MHLO dialect
for further lowering to the Linalg dialect.
This patch also updates all lit tests so that they refer to the
`convert-torch-to-stablehlo` pass and so that they check for StableHLO
operations.
Credit to @vivekkhandelwal1 for finding the necessary changes.
Summary of changes:
- Switch Tosa_IntArrayAttr[N], Tosa_IntArrayAttrUpto[N] to DenseI64ArrayAttr.
- Replace kNoIterationLimit with kNoLimit. (https://reviews.llvm.org/D140525)
- Add dependency on MhloPasses when MHLO is enabled
- Specify result type when using mhlo::DotOp
This commit replaces the `tanh` dtype function, which was being used
to test the implementation of dtype functions in
a710237437, with a dtype function for
`expm1`. The dtype function for `expm1` is identical to the `tanh`
one, so the same level of testing is maintained.
Currently, there are ops getting dtype information from the
`RefineTypes` pass and ops getting dtype information from the
`TorchDtypeRefinementPipeline`. Since each pass can only propagete
dtype information for the ops it knows how to handle, some models with
many ops handled in both passes require the two dtype propagation
passes to execute many times, reaching the iteration limit set in the
`LowerToBackendContractPass`. To temporarily avoid this issue while
the migration to `TorchDtypeRefinementPipeline` is finished, this
commit switches `tanh` to `expm1`, since the latter is used a lot less
in large models.
This reverts commit eaab9be207, since it
is causing the post-merge CI tests to fail, causing subsequent PRs to be
blocked. Specifically, the tests
`ElementwiseAtenLogicalAndOpPromoteBroadcastModule_basic` and
`ElementwiseAtenLogicalXorOpPromoteBroadcastModule_basic` fail because
the oracle does not match the computed result. This patch reverts the
commit to make the post-merge builds green again.
In order to verify if a given IR satisfies the backend contract, the
verifier needs to know if decompositions took place, and if so, which
ops were decomposed and which were not.
This commit adds two arguments to `verifyBackendContractPass` to
specify if decompositions took place and which ops to consider backend
legal, similar to the arguments of `LowerToBackendContractPass`.
* [custom op] Generalize shape library logic to work with dtypes
This commit generalizes the shape library logic, so that dtype rules
for ops can also be expressed using the same mechanism. In other
words, each op can now have a shape function and a dtype function
specified in Python that is imported during lowering to calculate the
shapes and dtypes throught a program. For more information about how
to specify a dtype function, see the updated
`docs/adding_a_shape_and_dtype_function.md`.
For those not familiar with how the shape library works, the file
`docs/calculations_lib.md` provides an overview.
The current implementation of `DecomposeComplexOps` fails if an op
expected to be decomposed does not get decomposed in the first
iteration of the `createTorchSimplificationPipeline` in
`LowerToBackendContractPass`. However, some graphs require multiple
iterations of `createTorchSimplificationPipeline` to fully propagate
all statically knowable information, such as dtypes and shapes, to the
entire graph, sometimes resulting in the need to run
`DecomposeComplexOps` more than once.
This commit changes `DecomposeComplexOps` to use a greedy algorithm
for pattern application and moves the legalization check of ops to the
`LowerToBackendContractPass` to allow for the `DecomposeComplexOps` to
run more than once.
- Support for non-prefixed accessors has been removed. See:
https://reviews.llvm.org/D136727
- Rename `operands` to `methodOperands` in `prim.CallMethod` since the
name `operands` overlaps with a builtin method name. See:
https://reviews.llvm.org/D136727
- Add passes in refbackend to lower memref.subview. See:
https://reviews.llvm.org/D136377
- Replace `CopyToValueTensorOps` first in `RewriteViewLikeSubgraph` in
maximize-value-semantics.
The current implementation of the `RewriteViewLikeSubgraph` pass in
maximize-value-semantics creates temporarily invalid IR. In
particular, given a forward slice starting from a
`CopyToNonValueTensorOp` and ending in `CopyToValueTensorOp`s, the
pass first replaces all uses of the `CopyToNonValueTensorOp` with
its operand, which results in all the `CopyToValueTensorOp` users
having their operand have type `!torch.vtensor`, which is invalid.
The correct way to do things is to first replace all the
`CopyToValueTensorOp`s with their operand, and then replace all uses
of the `CopyToNonValueTensorOp` with its operand.
This only started failing now because the generated accessor
`getOperand` for the `CopyToValueTensorOp` now returns a
`TypedValue<NonValueTensorType>`, which has an assert checking that
the value returned is of the expected type.
This commit changes the `InsertRngGlobalsPass` to `TorchConversionToMLProgram`
pass. This commit also adds the `MLProgramBufferize` pass for the
bufferization of ml_program dialect ops to run on refbackend.
Signed-Off By: Vivek Khandelwal<vivek@nod-labs.com>
Vivek Khandelwal
John Wu
Xida Ren (Cedar)
aldesilv
saienduri
Stella Laurenzo
Rik Huijzer
Rob Suderman
Andreas Falkenberg
Quinn Dawkins
Gaurav Shukla
Frederik Harwath
Sambhav Jain
Zhekun(Josh) Zhang
James Newling
Yuanqiang Liu
Daniel Garvey
Ze Zhang
Chi_Liu
Quinn Dawkins
Bruce Kim
JianzheXiao
jinchen62
Jiawei Wu
Ramiro Leal-Cavazos
Gleb Kazantaev
Matthias Gehre
Alexandre Rames
Jiawei Wu
Maksim Levental
Christopher McGirr
TatWai Chong
Sean Silva
Alexandre Rames
Michael Feliz
Ziheng Jiang
Ashay Rane
Raghavan Raman
Jiahao Li
Tanyo Kwok
zzp_miracle
Chi_Liu
ataheridezfouli-groq
Ahmed S. Taei