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
text-generation-inference
Commits
ce7e3565
Commit
ce7e3565
authored
Oct 15, 2024
by
Daniël de Kok
Browse files
Use flashinfer for Gemma 2.
parent
cf04a43f
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
1 addition
and
1 deletion
+1
-1
launcher/src/main.rs
launcher/src/main.rs
+1
-1
No files found.
launcher/src/main.rs
View file @
ce7e3565
...
...
@@ -94,7 +94,7 @@ fn resolve_attention(config: &Option<Config>, lora_adapters: &Option<String>) ->
prefix_caching
=
Some
(
"0"
.to_string
());
}
match
config
.model_type
.as_deref
()
{
Some
(
"gemma2"
)
|
Some
(
"falcon"
)
|
Some
(
"deepseek_v2"
)
=>
{
Some
(
"falcon"
)
|
Some
(
"deepseek_v2"
)
=>
{
// Required because gemma2 needs bfloat16 which is not supported by
// flashinfer ?
if
attention
.is_none
()
{
...
...
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