Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
Menu
Open sidebar
OpenDAS
vllm_cscc
Commits
66b809cc
Commit
66b809cc
authored
Feb 08, 2025
by
zhuwenwen
Browse files
Merge tag 'v0.7.2' into v0.7.2-dev
parents
37b63c24
0408efc6
Changes
1000
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
34 additions
and
1 deletion
+34
-1
vllm/lora/ops/torch_ops/__init__.py
vllm/lora/ops/torch_ops/__init__.py
+2
-0
vllm/lora/ops/torch_ops/lora_ops.py
vllm/lora/ops/torch_ops/lora_ops.py
+2
-0
vllm/lora/ops/triton_ops/__init__.py
vllm/lora/ops/triton_ops/__init__.py
+2
-0
vllm/lora/ops/triton_ops/bgmv_expand.py
vllm/lora/ops/triton_ops/bgmv_expand.py
+1
-0
vllm/lora/ops/triton_ops/bgmv_expand_slice.py
vllm/lora/ops/triton_ops/bgmv_expand_slice.py
+1
-0
vllm/lora/ops/triton_ops/bgmv_shrink.py
vllm/lora/ops/triton_ops/bgmv_shrink.py
+1
-0
vllm/lora/ops/triton_ops/sgmv_expand.py
vllm/lora/ops/triton_ops/sgmv_expand.py
+1
-0
vllm/lora/ops/triton_ops/sgmv_shrink.py
vllm/lora/ops/triton_ops/sgmv_shrink.py
+1
-0
vllm/lora/ops/triton_ops/utils.py
vllm/lora/ops/triton_ops/utils.py
+2
-0
vllm/lora/peft_helper.py
vllm/lora/peft_helper.py
+2
-0
vllm/lora/punica_wrapper/__init__.py
vllm/lora/punica_wrapper/__init__.py
+2
-0
vllm/lora/punica_wrapper/punica_base.py
vllm/lora/punica_wrapper/punica_base.py
+1
-0
vllm/lora/punica_wrapper/punica_cpu.py
vllm/lora/punica_wrapper/punica_cpu.py
+2
-0
vllm/lora/punica_wrapper/punica_gpu.py
vllm/lora/punica_wrapper/punica_gpu.py
+1
-0
vllm/lora/punica_wrapper/punica_hpu.py
vllm/lora/punica_wrapper/punica_hpu.py
+2
-0
vllm/lora/punica_wrapper/punica_selector.py
vllm/lora/punica_wrapper/punica_selector.py
+2
-0
vllm/lora/punica_wrapper/utils.py
vllm/lora/punica_wrapper/utils.py
+2
-0
vllm/lora/request.py
vllm/lora/request.py
+3
-1
vllm/lora/utils.py
vllm/lora/utils.py
+2
-0
vllm/lora/worker_manager.py
vllm/lora/worker_manager.py
+2
-0
No files found.
Too many changes to show.
To preserve performance only
1000 of 1000+
files are displayed.
Plain diff
Email patch
vllm/lora/ops/torch_ops/__init__.py
View file @
66b809cc
# SPDX-License-Identifier: Apache-2.0
from
vllm.lora.ops.torch_ops.lora_ops
import
bgmv_expand
# noqa: F401
from
vllm.lora.ops.torch_ops.lora_ops
import
bgmv_expand
# noqa: F401
from
vllm.lora.ops.torch_ops.lora_ops
import
(
bgmv_expand_slice
,
bgmv_shrink
,
from
vllm.lora.ops.torch_ops.lora_ops
import
(
bgmv_expand_slice
,
bgmv_shrink
,
sgmv_expand
,
sgmv_expand_slice
,
sgmv_expand
,
sgmv_expand_slice
,
...
...
vllm/lora/ops/torch_ops/lora_ops.py
View file @
66b809cc
# SPDX-License-Identifier: Apache-2.0
import
torch
import
torch
...
...
vllm/lora/ops/triton_ops/__init__.py
View file @
66b809cc
# SPDX-License-Identifier: Apache-2.0
from
vllm.lora.ops.triton_ops.bgmv_expand
import
bgmv_expand
from
vllm.lora.ops.triton_ops.bgmv_expand
import
bgmv_expand
from
vllm.lora.ops.triton_ops.bgmv_expand_slice
import
bgmv_expand_slice
from
vllm.lora.ops.triton_ops.bgmv_expand_slice
import
bgmv_expand_slice
from
vllm.lora.ops.triton_ops.bgmv_shrink
import
bgmv_shrink
from
vllm.lora.ops.triton_ops.bgmv_shrink
import
bgmv_shrink
...
...
vllm/lora/ops/triton_ops/bgmv_expand.py
View file @
66b809cc
# SPDX-License-Identifier: Apache-2.0
"""
"""
Based on:
Based on:
Chen, L., Ye, Z., Wu, Y., Zhuo, D., Ceze, L., & Krishnamurthy, A. (2023).
Chen, L., Ye, Z., Wu, Y., Zhuo, D., Ceze, L., & Krishnamurthy, A. (2023).
...
...
vllm/lora/ops/triton_ops/bgmv_expand_slice.py
View file @
66b809cc
# SPDX-License-Identifier: Apache-2.0
"""
"""
Based on:
Based on:
Chen, L., Ye, Z., Wu, Y., Zhuo, D., Ceze, L., & Krishnamurthy, A. (2023).
Chen, L., Ye, Z., Wu, Y., Zhuo, D., Ceze, L., & Krishnamurthy, A. (2023).
...
...
vllm/lora/ops/triton_ops/bgmv_shrink.py
View file @
66b809cc
# SPDX-License-Identifier: Apache-2.0
"""
"""
Based on:
Based on:
Chen, L., Ye, Z., Wu, Y., Zhuo, D., Ceze, L., & Krishnamurthy, A. (2023).
Chen, L., Ye, Z., Wu, Y., Zhuo, D., Ceze, L., & Krishnamurthy, A. (2023).
...
...
vllm/lora/ops/triton_ops/sgmv_expand.py
View file @
66b809cc
# SPDX-License-Identifier: Apache-2.0
"""
"""
Based on:
Based on:
Chen, L., Ye, Z., Wu, Y., Zhuo, D., Ceze, L., & Krishnamurthy, A. (2023).
Chen, L., Ye, Z., Wu, Y., Zhuo, D., Ceze, L., & Krishnamurthy, A. (2023).
...
...
vllm/lora/ops/triton_ops/sgmv_shrink.py
View file @
66b809cc
# SPDX-License-Identifier: Apache-2.0
"""
"""
Based on:
Based on:
Chen, L., Ye, Z., Wu, Y., Zhuo, D., Ceze, L., & Krishnamurthy, A. (2023).
Chen, L., Ye, Z., Wu, Y., Zhuo, D., Ceze, L., & Krishnamurthy, A. (2023).
...
...
vllm/lora/ops/triton_ops/utils.py
View file @
66b809cc
# SPDX-License-Identifier: Apache-2.0
import
functools
import
functools
from
typing
import
Dict
,
List
,
Tuple
from
typing
import
Dict
,
List
,
Tuple
...
...
vllm/lora/peft_helper.py
View file @
66b809cc
# SPDX-License-Identifier: Apache-2.0
# Adapted from: https://github.com/huggingface/peft/blob/main/src/peft/tuners/lora/config.py
# Adapted from: https://github.com/huggingface/peft/blob/main/src/peft/tuners/lora/config.py
import
json
import
json
...
...
vllm/lora/punica_wrapper/__init__.py
View file @
66b809cc
# SPDX-License-Identifier: Apache-2.0
from
vllm.lora.punica_wrapper.punica_base
import
PunicaWrapperBase
from
vllm.lora.punica_wrapper.punica_base
import
PunicaWrapperBase
from
vllm.lora.punica_wrapper.punica_selector
import
get_punica_wrapper
from
vllm.lora.punica_wrapper.punica_selector
import
get_punica_wrapper
...
...
vllm/lora/punica_wrapper/punica_base.py
View file @
66b809cc
# SPDX-License-Identifier: Apache-2.0
"""
"""
Based on:
Based on:
Chen, L., Ye, Z., Wu, Y., Zhuo, D., Ceze, L., & Krishnamurthy, A. (2023).
Chen, L., Ye, Z., Wu, Y., Zhuo, D., Ceze, L., & Krishnamurthy, A. (2023).
...
...
vllm/lora/punica_wrapper/punica_cpu.py
View file @
66b809cc
# SPDX-License-Identifier: Apache-2.0
from
typing
import
Callable
,
Optional
,
Tuple
,
Union
from
typing
import
Callable
,
Optional
,
Tuple
,
Union
import
torch
import
torch
...
...
vllm/lora/punica_wrapper/punica_gpu.py
View file @
66b809cc
# SPDX-License-Identifier: Apache-2.0
"""
"""
Based on:
Based on:
Chen, L., Ye, Z., Wu, Y., Zhuo, D., Ceze, L., & Krishnamurthy, A. (2023).
Chen, L., Ye, Z., Wu, Y., Zhuo, D., Ceze, L., & Krishnamurthy, A. (2023).
...
...
vllm/lora/punica_wrapper/punica_hpu.py
View file @
66b809cc
# SPDX-License-Identifier: Apache-2.0
from
typing
import
Optional
,
Tuple
,
Union
,
final
from
typing
import
Optional
,
Tuple
,
Union
,
final
import
torch
import
torch
...
...
vllm/lora/punica_wrapper/punica_selector.py
View file @
66b809cc
# SPDX-License-Identifier: Apache-2.0
from
vllm.logger
import
init_logger
from
vllm.logger
import
init_logger
from
vllm.platforms
import
current_platform
from
vllm.platforms
import
current_platform
from
vllm.utils
import
resolve_obj_by_qualname
from
vllm.utils
import
resolve_obj_by_qualname
...
...
vllm/lora/punica_wrapper/utils.py
View file @
66b809cc
# SPDX-License-Identifier: Apache-2.0
from
typing
import
TYPE_CHECKING
,
List
,
Optional
,
Tuple
,
Union
from
typing
import
TYPE_CHECKING
,
List
,
Optional
,
Tuple
,
Union
import
torch
import
torch
...
...
vllm/lora/request.py
View file @
66b809cc
# SPDX-License-Identifier: Apache-2.0
import
warnings
import
warnings
from
typing
import
Optional
from
typing
import
Optional
...
@@ -31,7 +33,7 @@ class LoRARequest(
...
@@ -31,7 +33,7 @@ class LoRARequest(
base_model_name
:
Optional
[
str
]
=
msgspec
.
field
(
default
=
None
)
base_model_name
:
Optional
[
str
]
=
msgspec
.
field
(
default
=
None
)
def
__post_init__
(
self
):
def
__post_init__
(
self
):
if
'
lora_local_path
'
in
self
.
__struct_fields__
:
if
self
.
lora_local_path
:
warnings
.
warn
(
warnings
.
warn
(
"The 'lora_local_path' attribute is deprecated "
"The 'lora_local_path' attribute is deprecated "
"and will be removed in a future version. "
"and will be removed in a future version. "
...
...
vllm/lora/utils.py
View file @
66b809cc
# SPDX-License-Identifier: Apache-2.0
import
os
import
os
import
re
import
re
from
typing
import
List
,
Optional
,
Set
,
Tuple
,
Type
,
Union
from
typing
import
List
,
Optional
,
Set
,
Tuple
,
Type
,
Union
...
...
vllm/lora/worker_manager.py
View file @
66b809cc
# SPDX-License-Identifier: Apache-2.0
from
contextlib
import
contextmanager
from
contextlib
import
contextmanager
from
typing
import
Any
,
Dict
,
List
,
Literal
,
Optional
,
Set
,
Type
,
Union
from
typing
import
Any
,
Dict
,
List
,
Literal
,
Optional
,
Set
,
Type
,
Union
...
...
Prev
1
…
30
31
32
33
34
35
36
37
38
…
50
Next
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment