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
d6459b45
Unverified
Commit
d6459b45
authored
Nov 02, 2024
by
Robert Shaw
Committed by
GitHub
Nov 02, 2024
Browse files
[V1] Fix `EngineArgs` refactor on V1 (#9954)
parent
e8937954
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
12 additions
and
27 deletions
+12
-27
vllm/v1/executor/gpu_executor.py
vllm/v1/executor/gpu_executor.py
+12
-27
No files found.
vllm/v1/executor/gpu_executor.py
View file @
d6459b45
import
os
import
os
from
typing
import
Optional
,
Tuple
from
typing
import
Optional
,
Tuple
from
vllm.config
import
(
CacheConfig
,
DeviceConfig
,
LoadConfig
,
LoRAConfig
,
from
vllm.config
import
EngineConfig
ModelConfig
,
ObservabilityConfig
,
ParallelConfig
,
PromptAdapterConfig
,
SchedulerConfig
,
SpeculativeConfig
)
from
vllm.logger
import
init_logger
from
vllm.logger
import
init_logger
from
vllm.utils
import
get_distributed_init_method
,
get_ip
,
get_open_port
from
vllm.utils
import
get_distributed_init_method
,
get_ip
,
get_open_port
from
vllm.v1.outputs
import
ModelRunnerOutput
from
vllm.v1.outputs
import
ModelRunnerOutput
...
@@ -15,29 +12,17 @@ logger = init_logger(__name__)
...
@@ -15,29 +12,17 @@ logger = init_logger(__name__)
class
GPUExecutor
:
class
GPUExecutor
:
def
__init__
(
def
__init__
(
self
,
vllm_config
:
EngineConfig
)
->
None
:
self
,
self
.
model_config
=
vllm_config
.
model_config
model_config
:
ModelConfig
,
self
.
cache_config
=
vllm_config
.
cache_config
cache_config
:
CacheConfig
,
self
.
lora_config
=
vllm_config
.
lora_config
parallel_config
:
ParallelConfig
,
self
.
load_config
=
vllm_config
.
load_config
scheduler_config
:
SchedulerConfig
,
self
.
parallel_config
=
vllm_config
.
parallel_config
device_config
:
DeviceConfig
,
self
.
scheduler_config
=
vllm_config
.
scheduler_config
load_config
:
LoadConfig
,
self
.
device_config
=
vllm_config
.
device_config
lora_config
:
Optional
[
LoRAConfig
],
self
.
speculative_config
=
vllm_config
.
speculative_config
speculative_config
:
Optional
[
SpeculativeConfig
],
self
.
prompt_adapter_config
=
vllm_config
.
prompt_adapter_config
prompt_adapter_config
:
Optional
[
PromptAdapterConfig
],
self
.
observability_config
=
vllm_config
.
observability_config
observability_config
:
Optional
[
ObservabilityConfig
],
)
->
None
:
self
.
model_config
=
model_config
self
.
cache_config
=
cache_config
self
.
lora_config
=
lora_config
self
.
load_config
=
load_config
self
.
parallel_config
=
parallel_config
self
.
scheduler_config
=
scheduler_config
self
.
device_config
=
device_config
self
.
speculative_config
=
speculative_config
self
.
prompt_adapter_config
=
prompt_adapter_config
self
.
observability_config
=
observability_config
self
.
worker
=
self
.
_create_worker
()
self
.
worker
=
self
.
_create_worker
()
self
.
worker
.
initialize
()
self
.
worker
.
initialize
()
...
...
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