Skip to content

[Executorch][llama] Renamed quantized_kv_cache to custom_kv_cache #9944

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

Merged
merged 4 commits into from
Apr 10, 2025
Merged

[Executorch][llama] Renamed quantized_kv_cache to custom_kv_cache #9944

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
e6dfe18
[Executorch][llama] Renamed quantized_kv_cache to custom_kv_cache
kimishpatel Apr 7, 2025
1820d86
Update on "[Executorch][llama] Renamed quantized_kv_cache to custom_k…
kimishpatel Apr 8, 2025
a6f00b4
Update on "[Executorch][llama] Renamed quantized_kv_cache to custom_k…
kimishpatel Apr 9, 2025
36ffe45
Update on "[Executorch][llama] Renamed quantized_kv_cache to custom_k…
kimishpatel Apr 10, 2025
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
10 changes: 5 additions & 5 deletions examples/models/llama/TARGETS
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -108,7 +108,7 @@ runtime.python_library(
"source_transformation/pre_quantization.py",
"source_transformation/prune_vocab.py",
"source_transformation/quantize.py",
"source_transformation/quantized_kv_cache.py",
"source_transformation/custom_kv_cache.py",
"source_transformation/rms_norm.py",
"source_transformation/rope.py",
"source_transformation/sdpa.py",
Expand Down Expand Up @@ -208,9 +208,9 @@ runtime.python_library(
)

runtime.python_library(
name = "quantized_kv_cache",
name = "custom_kv_cache",
srcs = [
"source_transformation/quantized_kv_cache.py",
"source_transformation/custom_kv_cache.py",
],
_is_external_target = True,
visibility = ["//executorch/..."],
Expand Down Expand Up @@ -240,7 +240,7 @@ runtime.python_test(
"//executorch/extension/llm/custom_ops:custom_ops_aot_lib",
],
deps = [
":quantized_kv_cache",
":custom_kv_cache",
"//caffe2:torch",
"//executorch/examples/models/llama:llama_transformer",
],
Expand All @@ -255,7 +255,7 @@ runtime.python_test(
"//executorch/extension/llm/custom_ops:custom_ops_aot_lib",
],
deps = [
":quantized_kv_cache",
":custom_kv_cache",
":sdpa",
"//caffe2:torch",
"//executorch/examples/models/llama:llama_transformer",
Expand Down
8 changes: 4 additions & 4 deletions examples/models/llama/export_llama_lib.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,14 +59,14 @@
)

from .source_transformation.attention import replace_attention_to_attention_sha
from .source_transformation.custom_kv_cache import (
replace_kv_cache_with_custom_kv_cache,
replace_kv_cache_with_quantized_kv_cache,
)
from .source_transformation.quantize import (
get_quant_embedding_transform,
get_quant_weight_transform,
)
from .source_transformation.quantized_kv_cache import (
replace_kv_cache_with_custom_kv_cache,
replace_kv_cache_with_quantized_kv_cache,
)
from .source_transformation.rms_norm import replace_rms_norm_with_native_rms_norm

from .source_transformation.rope import materialze_broadcast_of_rope_freq_cis
Expand Down
0 ...urce_transformation/quantized_kv_cache.py → .../source_transformation/custom_kv_cache.py
View file
Open in desktop
File renamed without changes.
2 changes: 1 addition & 1 deletion examples/models/llama/source_transformation/test_quantized_kv_cache.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@

from executorch.examples.models.llama.attention import KVCache

from executorch.examples.models.llama.source_transformation.quantized_kv_cache import (
from executorch.examples.models.llama.source_transformation.custom_kv_cache import (
QuantizedCacheType,
QuantizedKVCache,
)
Expand Down
2 changes: 1 addition & 1 deletion examples/models/llama/source_transformation/test_sdpa_with_quantized_kv_cache.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@

from executorch.examples.models.llama.attention import KVCache

from executorch.examples.models.llama.source_transformation.quantized_kv_cache import (
from executorch.examples.models.llama.source_transformation.custom_kv_cache import (
CustomKVCache,
QuantizedCacheType,
QuantizedKVCache,
Expand Down
6 changes: 3 additions & 3 deletions examples/models/llava/export_llava.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,13 +20,13 @@
build_args_parser,
get_quantizer_and_quant_params,
)
from executorch.examples.models.llama.source_transformation.custom_kv_cache import (
replace_kv_cache_with_custom_kv_cache,
)
from executorch.examples.models.llama.source_transformation.quantize import (
EmbeddingQuantHandler,
get_quant_weight_transform,
)
from executorch.examples.models.llama.source_transformation.quantized_kv_cache import (
replace_kv_cache_with_custom_kv_cache,
)
from executorch.examples.models.llama.source_transformation.sdpa import (
replace_sdpa_with_custom_op,
)
Expand Down
2 changes: 1 addition & 1 deletion examples/models/llava/model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@
from executorch.examples.models.llama.llama_transformer import Transformer
from executorch.examples.models.llama.model_args import ModelArgs

from executorch.examples.models.llama.source_transformation.quantized_kv_cache import (
from executorch.examples.models.llama.source_transformation.custom_kv_cache import (
replace_kv_cache_with_custom_kv_cache,
)
from executorch.examples.models.llama.source_transformation.sdpa import (
Expand Down
Loading