diff --git a/tools/ui/src/lib/components/app/models/ModelsManager/ModelsManagerModelConfiguration/ModelsManagerModelConfiguration.svelte b/tools/ui/src/lib/components/app/models/ModelsManager/ModelsManagerModelConfiguration/ModelsManagerModelConfiguration.svelte index 1cf1188e35..b6ee1835bc 100644 --- a/tools/ui/src/lib/components/app/models/ModelsManager/ModelsManagerModelConfiguration/ModelsManagerModelConfiguration.svelte +++ b/tools/ui/src/lib/components/app/models/ModelsManager/ModelsManagerModelConfiguration/ModelsManagerModelConfiguration.svelte @@ -30,7 +30,12 @@ let edits = $state(null); let draft = $derived(edits ?? override ?? {}); - let serverProps = $derived(modelsStore.props.getModelProps(option.model)); + // the props cache is a plain Map, so the read has to name its version to stay reactive + let serverProps = $derived.by(() => { + void modelsStore.props.cacheVersion; + + return modelsStore.props.getModelProps(option.model); + }); let status = $derived.by(() => { const model = modelsStore.routerModels.find((m) => m.id === option.model); diff --git a/tools/ui/src/lib/components/app/models/ModelsManager/ModelsManagerModelConfiguration/ModelsManagerModelConfigurationHeader.svelte b/tools/ui/src/lib/components/app/models/ModelsManager/ModelsManagerModelConfiguration/ModelsManagerModelConfigurationHeader.svelte index a6fc6e47bb..71edb2ca8d 100644 --- a/tools/ui/src/lib/components/app/models/ModelsManager/ModelsManagerModelConfiguration/ModelsManagerModelConfigurationHeader.svelte +++ b/tools/ui/src/lib/components/app/models/ModelsManager/ModelsManagerModelConfiguration/ModelsManagerModelConfigurationHeader.svelte @@ -7,6 +7,7 @@ import { ModelCapability, ServerModelStatus } from '$lib/enums'; import type { ModelOption } from '$lib/types/models'; import { getBackend } from '$lib/utils/api-base'; + import { getBackendCapabilities } from '$lib/utils/backend'; interface Props { isCustomized: boolean; @@ -24,7 +25,16 @@ let supportsToolUse = $derived(option.capabilities.includes(ModelCapability.TOOL_USE)); let supportsThinking = $derived(option.capabilities.includes(ModelCapability.REASONING)); - let backendName = $derived(getBackend(option.backendId)?.name ?? null); + let backend = $derived(getBackend(option.backendId)); + let backendName = $derived(backend?.name ?? null); + let capabilities = $derived(getBackendCapabilities(backend)); + // what the provider speaks decides which server endpoints the pane can read + let compatLabel = $derived(backend?.protocol === 'llama.cpp' ? 'Llama-compat' : 'OAI-compat'); + let compatTitle = $derived( + capabilities.props + ? 'llama.cpp server: reads /props and /slots' + : 'OpenAI-compatible: no /props, /slots, load or unload' + ); // the listing usually carries the size; a local repo falls back to its tree let size = $state(null); @@ -134,6 +144,10 @@ {backendName} {/if} + + + {compatLabel} +
@@ -143,16 +157,18 @@ Start a new chat - + Load model + {/if} + + {/if}
diff --git a/tools/ui/src/lib/components/app/models/ModelsManager/ModelsManagerModelConfiguration/ModelsManagerModelConfigurationInformation.svelte b/tools/ui/src/lib/components/app/models/ModelsManager/ModelsManagerModelConfiguration/ModelsManagerModelConfigurationInformation.svelte index 0856fce628..0bfef214a2 100644 --- a/tools/ui/src/lib/components/app/models/ModelsManager/ModelsManagerModelConfiguration/ModelsManagerModelConfigurationInformation.svelte +++ b/tools/ui/src/lib/components/app/models/ModelsManager/ModelsManagerModelConfiguration/ModelsManagerModelConfigurationInformation.svelte @@ -17,6 +17,8 @@ import type { ApiLlamaCppServerProps } from '$lib/types/api'; import type { HfModelDetailInfo } from '$lib/types/huggingface'; import type { ModelOption } from '$lib/types/models'; + import { getBackend } from '$lib/utils/api-base'; + import { getBackendCapabilities } from '$lib/utils/backend'; import { formatFileSize, formatNumber, formatParameters } from '$lib/utils/formatters'; interface Props { @@ -68,17 +70,32 @@ let activeDraft = $derived(drafts.find((draft) => draft.active) ?? null); let idleDrafts = $derived(drafts.filter((draft) => !draft.active)); let meta = $derived(option.meta); + // a plain OpenAI-compatible endpoint has no /props or /slots to read + let reportsServerInfo = $derived(getBackendCapabilities(getBackend(option.backendId)).props); // the server reports these once the model is loaded; the Hub knows them anyway let gguf = $derived(hub?.gguf ?? null); - let modalities = $derived(modelsStore.props.getModelModalitiesArray(option.id)); + let modalities = $derived.by(() => { + void modelsStore.props.cacheVersion; + + return modelsStore.props.getModelModalitiesArray(option.id); + }); let rows = $derived([ - { isCopyable: true, isMono: true, label: 'File Path', value: serverProps?.model_path ?? null }, + ...(reportsServerInfo + ? [ + { + isCopyable: true, + isMono: true, + label: 'File Path', + value: serverProps?.model_path ?? null + } + ] + : []), { label: 'Context Size', // the server reports the context it runs with once the model is loaded; until then // the listing, or the Hub, still says what the model can take value: serverProps - ? `${formatNumber(serverProps.default_generation_settings.n_ctx)} tokens` + ? `${formatNumber(serverProps.default_generation_settings?.n_ctx ?? 0)} tokens` : (contextLabel ?? null) }, { label: 'Training Context', value: contextLabel }, @@ -121,8 +138,15 @@ label: 'Other sidecars', value: idleDrafts.length > 0 ? idleDrafts.map((draft) => draft.kind).join(', ') : null }, - { label: 'Parallel Slots', value: serverProps ? String(serverProps.total_slots) : null }, - { isMono: true, label: 'Build Info', value: serverProps?.build_info ?? null } + ...(reportsServerInfo + ? [ + { + label: 'Parallel Slots', + value: serverProps?.total_slots != null ? String(serverProps.total_slots) : null + }, + { isMono: true, label: 'Build Info', value: serverProps?.build_info ?? null } + ] + : []) ] satisfies Array<{ isBadge?: boolean; isCapitalized?: boolean; @@ -202,9 +226,15 @@ {/if} -{#if hub} +{#if !reportsServerInfo}

- Some values come from the Hugging Face Hub. Load the model to read them from the server. + OpenAI-compatible provider: there is no /props or /slots, so only what the listing and the + model's repo report is shown. +

+{:else if !serverProps} +

+ /props values - file path, slots, build info - appear once the model is loaded. Reading this + page never loads a model.

{/if} @@ -220,15 +250,17 @@ 'Not reported by the server.'} - - {#snippet trigger()} - Source File - {/snippet} + {#if reportsServerInfo} + + {#snippet trigger()} + Source File + {/snippet} -
-

- {serverProps?.model_path ?? 'Path is reported once the model is loaded.'} -

-
- +
+

+ {serverProps?.model_path ?? 'Path is reported once the model is loaded.'} +

+
+ + {/if}