Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

#5389: removed early return from validate when enable_fast_runtime_mo… #8983

Merged
merged 2 commits into from
Jun 4, 2024
Merged

#5389: removed early return from validate when enable_fast_runtime_mo… #8983

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
58e7370
#5389: removed early return from validate when enable_fast_runtime_mo…
arakhmati May 30, 2024
798628c
#0: fix matmul dram sharded validation
yugaoTT Jun 3, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions tests/ttnn/integration_tests/mistral/test_mistral_attention.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,8 @@

# SPDX-License-Identifier: Apache-2.0

import pytest

import torch
import ttnn
import tt_lib
Expand All @@ -19,6 +21,7 @@
from tests.ttnn.utils_for_testing import assert_with_pcc


@pytest.mark.skip(reason="https://github.com/tenstorrent/tt-metal/issues/9076")
@skip_for_wormhole_b0()
def test_mistral_attention_inference(model_location_generator, device, reset_seeds):
model_path = model_location_generator("mistral-7B-v0.1", model_subdir="Mistral")
Expand Down
2 changes: 1 addition & 1 deletion tt_eager/tt_dnn/op_library/bmm/bmm_op.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1041,7 +1041,7 @@ void Matmul::validate(
// subbblock constraint
TT_FATAL(program_config.out_subblock_w == per_core_N || program_config.out_subblock_h == 1);
// tensor in1
TT_FATAL(input_tensor_b.memory_config().memory_layout == TensorMemoryLayout::INTERLEAVED);
TT_FATAL(input_tensor_b.memory_config().memory_layout == TensorMemoryLayout::WIDTH_SHARDED);
} else if constexpr (std::is_same_v<ProgramConfigType, MatmulMultiCoreReuseMultiCastProgramConfig>) {
if (input_tensor_a.memory_config().is_sharded()) {
auto tensor_a_memory_layout = input_tensor_a.memory_config().memory_layout;
Expand Down
3 changes: 0 additions & 3 deletions tt_eager/tt_dnn/op_library/operation.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -528,9 +528,6 @@ struct DeviceOperation final {
const Tensors& input_tensors,
const OptionalConstTensors& optional_input_tensors,
const OptionalTensors& optional_output_tensors) -> void {
if (ttnn::CONFIG.enable_fast_runtime_mode) {
return;
}
const auto& operation = *reinterpret_cast<const std::decay_t<T>*>(&storage);
if constexpr (
(detail::implements_validate<T>() or
Expand Down
2 changes: 1 addition & 1 deletion ttnn/ttnn/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,7 +57,7 @@ def validate(self, name):
if self.enable_fast_runtime_mode:
if self.enable_logging:
logger.warning(
"Running in fast runtime mode without logging. Please disable fast runtime mode if you want to enable logging."
"Logging cannot be enabled in fast runtime mode. Please disable fast runtime mode if you want to enable logging."
)

if name in {
Expand Down
Loading