From ce7e35656127cbd0c5b4ddff074365a6201a206a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Dani=C3=ABl=20de=20Kok?= <me@danieldk.eu>
Date: Tue, 15 Oct 2024 13:49:32 +0000
Subject: [PATCH] Use flashinfer for Gemma 2.

---
 launcher/src/main.rs | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/launcher/src/main.rs b/launcher/src/main.rs
index 42962dffb..ee259e434 100644
--- a/launcher/src/main.rs
+++ b/launcher/src/main.rs
@@ -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() {