mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-08-01 23:50:47 -05:00
555881ebc8
* performance harness - the empirical root Assisted-by: Claude Opus 4.8 * 210.36ms -> 2.67ms per streamed token Assisted-by: Claude Opus 4.8 * 11.58ms -> 0.62ms per streamed token Assisted-by: Claude Opus 4.8 * 22.02ms -> 3.33ms per streamed token Assisted-by: Claude Opus 4.8 * 3.07ms -> 1.36ms per streamed token at 40 messages Assisted-by: Claude Opus 4.8 --------- Co-authored-by: Zach Winter <dmtommy@icloud.com>
13 lines
564 B
Svelte
13 lines
564 B
Svelte
<script lang="ts">
|
|
// Mounts the real ChatMessages list against the real conversations store, so
|
|
// the harness exercises `displayMessages` (which rebuilds every message's
|
|
// toolMessages array) rather than a single message subtree.
|
|
import * as Tooltip from '$lib/components/ui/tooltip';
|
|
import ChatMessages from '$lib/components/app/chat/ChatMessages/ChatMessages.svelte';
|
|
import { conversationsStore } from '$lib/stores/conversations.svelte';
|
|
</script>
|
|
|
|
<Tooltip.Provider>
|
|
<ChatMessages messages={conversationsStore.activeMessages} />
|
|
</Tooltip.Provider>
|