Skip to content

Delete llama_quantized lib #3119

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

Closed
wants to merge 1 commit into from
Closed

Delete llama_quantized lib #3119

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
23 changes: 3 additions & 20 deletions examples/models/llama2/CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,6 @@ set(EXECUTORCH_ROOT ${CMAKE_CURRENT_SOURCE_DIR}/../../..)
set(TORCH_ROOT ${EXECUTORCH_ROOT}/third-party/pytorch)

include(${EXECUTORCH_ROOT}/build/Utils.cmake)
include(${EXECUTORCH_ROOT}/build/Codegen.cmake)

if(NOT PYTHON_EXECUTABLE)
resolve_python_executable()
Expand Down Expand Up @@ -120,25 +119,9 @@ else()
target_link_options_shared_lib(portable_ops_lib)
endif()

# quantized ops yaml file operation
merge_yaml(
FUNCTIONS_YAML ${CMAKE_CURRENT_SOURCE_DIR}/ops/quantized.yaml
FALLBACK_YAML ${EXECUTORCH_ROOT}/kernels/quantized/quantized.yaml
OUTPUT_DIR ${CMAKE_CURRENT_BINARY_DIR})

gen_selected_ops("${CMAKE_CURRENT_BINARY_DIR}/merged.yaml" "" "")
generate_bindings_for_kernels(
FUNCTIONS_YAML ${CMAKE_CURRENT_BINARY_DIR}/merged.yaml)
message("Generated files ${gen_command_sources}")

# quantized_merge_ops_lib: Register quantized op kernels into the runtime
gen_operators_lib(
"quantized_merge_ops_lib"
KERNEL_LIBS quantized_kernels
DEPS executorch)
target_include_directories(quantized_merge_ops_lib PUBLIC ${_common_include_directories})
target_link_options_shared_lib(quantized_merge_ops_lib)
list(APPEND link_libraries quantized_kernels quantized_merge_ops_lib)
# quantized_ops_lib: Register quantized op kernels into the runtime
target_link_options_shared_lib(quantized_ops_lib)
list(APPEND link_libraries quantized_kernels quantized_ops_lib)

if(EXECUTORCH_BUILD_CUSTOM)
target_link_options_shared_lib(custom_ops)
Expand Down
1 change: 0 additions & 1 deletion examples/models/llama2/TARGETS
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,6 @@ runtime.python_library(
"//caffe2:torch",
"//executorch/examples/models:model_base",
"//executorch/examples/models/llama2:llama_transformer",
"//executorch/examples/models/llama2/ops:quantized_aot_lib",
],
)

Expand Down
5 changes: 0 additions & 5 deletions examples/models/llama2/ops/TARGETS
View file
Open in desktop

This file was deleted.

11 changes: 0 additions & 11 deletions examples/models/llama2/ops/quantized.yaml
View file
Open in desktop

This file was deleted.

169 changes: 0 additions & 169 deletions examples/models/llama2/ops/quantized_ops.py
View file
Open in desktop

This file was deleted.

50 changes: 0 additions & 50 deletions examples/models/llama2/ops/targets.bzl
View file
Open in desktop

This file was deleted.

6 changes: 4 additions & 2 deletions examples/models/llama2/quantize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,9 @@
import torch
import torch.nn as nn
import torch.nn.functional as F
from .ops.quantized_ops import * # noqa
from executorch.exir.passes._quant_patterns_and_replacements import ( # noqa
quantized_decomposed_lib,
)


try:
Expand Down Expand Up @@ -377,7 +379,7 @@ def __init__(

@torch.no_grad()
def forward(self, indices: torch.Tensor) -> torch.Tensor:
return torch.ops.llama_quantized.DEPRECATED_DO_NOT_USE_embedding_byte.dtype(
return torch.ops.quantized_decomposed.embedding_byte.dtype(
self.weight, self.scales, None, 0, 0, indices, dtype=self.dtype
)

Expand Down
4 changes: 2 additions & 2 deletions examples/models/llama2/runner/targets.bzl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,9 +4,9 @@ def _get_operator_lib(aten = False):
if aten:
return ["//executorch/kernels/aten:generated_lib"]
elif runtime.is_oss:
return ["//executorch/kernels/portable:generated_lib", "//executorch/examples/models/llama2/custom_ops:custom_ops", "//executorch/examples/models/llama2/ops:generated_lib"]
return ["//executorch/kernels/portable:generated_lib", "//executorch/examples/models/llama2/custom_ops:custom_ops"]
else:
return ["//executorch/configurations:optimized_native_cpu_ops", "//executorch/examples/models/llama2/custom_ops:custom_ops", "//executorch/examples/models/llama2/ops:generated_lib"]
return ["//executorch/configurations:optimized_native_cpu_ops", "//executorch/examples/models/llama2/custom_ops:custom_ops"]

def define_common_targets():
for aten in (True, False):
Expand Down
Loading