Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
change
sglang
Commits
ce216c80
Unverified
Commit
ce216c80
authored
Mar 24, 2024
by
Qubitium
Committed by
GitHub
Mar 23, 2024
Browse files
Cleanup codebase: removed unnecessary code/logic (#298)
parent
51104cd4
Changes
3
Hide whitespace changes
Inline
Side-by-side
Showing
3 changed files
with
8 additions
and
8 deletions
+8
-8
python/sglang/srt/managers/router/manager.py
python/sglang/srt/managers/router/manager.py
+6
-2
python/sglang/srt/managers/router/model_rpc.py
python/sglang/srt/managers/router/model_rpc.py
+0
-1
python/sglang/srt/managers/tokenizer_manager.py
python/sglang/srt/managers/tokenizer_manager.py
+2
-5
No files found.
python/sglang/srt/managers/router/manager.py
View file @
ce216c80
...
...
@@ -41,12 +41,16 @@ class RouterManager:
self
.
send_to_detokenizer
.
send_pyobj
(
obj
)
# async sleep for receiving the subsequent request and avoiding cache miss
slept
=
False
if
len
(
out_pyobjs
)
!=
0
:
has_finished
=
any
([
obj
.
finished
for
obj
in
out_pyobjs
])
if
has_finished
:
await
asyncio
.
sleep
(
self
.
extend_dependency_time
)
if
self
.
extend_dependency_time
>
0
:
slept
=
True
await
asyncio
.
sleep
(
self
.
extend_dependency_time
)
await
asyncio
.
sleep
(
0.0006
)
if
not
slept
:
await
asyncio
.
sleep
(
0.0006
)
async
def
loop_for_recv_requests
(
self
):
while
True
:
...
...
python/sglang/srt/managers/router/model_rpc.py
View file @
ce216c80
...
...
@@ -90,7 +90,6 @@ class ModelRpcServer(rpyc.Service):
tokenizer_mode
=
server_args
.
tokenizer_mode
,
trust_remote_code
=
server_args
.
trust_remote_code
,
)
self
.
eos_token_id
=
self
.
tokenizer
.
eos_token_id
self
.
max_total_num_token
=
self
.
model_runner
.
max_total_num_token
self
.
max_num_running_seq
=
self
.
max_total_num_token
//
2
self
.
max_prefill_num_token
=
max
(
...
...
python/sglang/srt/managers/tokenizer_manager.py
View file @
ce216c80
...
...
@@ -36,7 +36,6 @@ class ReqState:
out_list
:
List
finished
:
bool
event
:
asyncio
.
Event
lock
:
asyncio
.
Lock
global
global_processor
...
...
@@ -178,9 +177,8 @@ class TokenizerManager:
)
self
.
send_to_router
.
send_pyobj
(
tokenized_obj
)
lock
=
asyncio
.
Lock
()
event
=
asyncio
.
Event
()
state
=
ReqState
([],
False
,
event
,
lock
)
state
=
ReqState
([],
False
,
event
)
self
.
rid_to_state
[
rid
]
=
state
while
True
:
...
...
@@ -221,9 +219,8 @@ class TokenizerManager:
)
self
.
send_to_router
.
send_pyobj
(
tokenized_obj
)
lock
=
asyncio
.
Lock
()
event
=
asyncio
.
Event
()
state
=
ReqState
([],
False
,
event
,
lock
)
state
=
ReqState
([],
False
,
event
)
self
.
rid_to_state
[
rid
]
=
state
output_list
=
[]
...
...
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