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>
17 lines
499 B
Svelte
17 lines
499 B
Svelte
<script lang="ts">
|
|
import * as Tooltip from '$lib/components/ui/tooltip';
|
|
import ChatMessageAgenticContent from '$lib/components/app/chat/ChatMessages/ChatMessageAgenticContent.svelte';
|
|
import { perfState } from './agentic-perf-state.svelte';
|
|
</script>
|
|
|
|
<Tooltip.Provider>
|
|
{#if perfState.message}
|
|
<ChatMessageAgenticContent
|
|
message={perfState.message}
|
|
toolMessages={perfState.toolMessages}
|
|
isStreaming={perfState.isStreaming}
|
|
isLastAssistantMessage
|
|
/>
|
|
{/if}
|
|
</Tooltip.Provider>
|