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
OpenDAS
Lmdeploy
Commits
7868cea5
You need to sign in or sign up before continuing.
Unverified
Commit
7868cea5
authored
Nov 27, 2023
by
Lyu Han
Committed by
GitHub
Nov 27, 2023
Browse files
Set the default value of `max_context_token_num` 1 (#761)
parent
4bcc4f11
Changes
3
Hide whitespace changes
Inline
Side-by-side
Showing
3 changed files
with
3 additions
and
3 deletions
+3
-3
docs/en/turbomind_config.md
docs/en/turbomind_config.md
+1
-1
docs/zh_cn/turbomind_config.md
docs/zh_cn/turbomind_config.md
+1
-1
lmdeploy/turbomind/deploy/target_model/base.py
lmdeploy/turbomind/deploy/target_model/base.py
+1
-1
No files found.
docs/en/turbomind_config.md
View file @
7868cea5
...
@@ -28,7 +28,7 @@ rope_theta = 10000.0
...
@@ -28,7 +28,7 @@ rope_theta = 10000.0
size_per_head
=
128
size_per_head
=
128
group_size
=
0
group_size
=
0
max_batch_size
=
64
max_batch_size
=
64
max_context_token_num
=
4
max_context_token_num
=
1
step_length
=
1
step_length
=
1
cache_max_entry_count
=
0.5
cache_max_entry_count
=
0.5
cache_block_seq_len
=
128
cache_block_seq_len
=
128
...
...
docs/zh_cn/turbomind_config.md
View file @
7868cea5
...
@@ -28,7 +28,7 @@ rope_theta = 10000.0
...
@@ -28,7 +28,7 @@ rope_theta = 10000.0
size_per_head
=
128
size_per_head
=
128
group_size
=
0
group_size
=
0
max_batch_size
=
64
max_batch_size
=
64
max_context_token_num
=
4
max_context_token_num
=
1
step_length
=
1
step_length
=
1
cache_max_entry_count
=
0.5
cache_max_entry_count
=
0.5
cache_block_seq_len
=
128
cache_block_seq_len
=
128
...
...
lmdeploy/turbomind/deploy/target_model/base.py
View file @
7868cea5
...
@@ -48,7 +48,7 @@ class TurbomindModelConfig:
...
@@ -48,7 +48,7 @@ class TurbomindModelConfig:
size_per_head
:
int
=
128
size_per_head
:
int
=
128
group_size
:
int
=
0
group_size
:
int
=
0
max_batch_size
:
int
=
64
max_batch_size
:
int
=
64
max_context_token_num
:
int
=
4
max_context_token_num
:
int
=
1
step_length
:
int
=
1
step_length
:
int
=
1
cache_max_entry_count
:
float
=
0.5
cache_max_entry_count
:
float
=
0.5
cache_block_seq_len
:
int
=
128
cache_block_seq_len
:
int
=
128
...
...
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