+ # 1. Serve a model
llama serve
@@ -184,29 +184,24 @@ pi
-
-
- Optimized for any hardware.
-
-
- From your laptop to a cluster, llama.cpp runs on whatever you have. Same binary, same
- models, same hand-tuned kernels for every GPU and CPU.
-
-
-
+
{#each HARDWARE_REELS as reel, reelIndex (reelIndex)}
- {#each Array(2) as _, copyIndex (copyIndex)}
+ {#each Array(2), copyIndex (copyIndex)}
{#each reel.items as hw (copyIndex + hw.name)}
-

+
{hw.name}
{/each}
@@ -216,6 +211,15 @@ pi
{/each}
+
+
+ Optimized for any hardware.
+
+
+ From your laptop to a cluster, llama.cpp runs on whatever you have. Same binary, same
+ models, same hand-tuned kernels for every GPU and CPU.
+
+
@@ -225,7 +229,7 @@ pi
{#each repos as repo (repo.id)}