root/gpustack-ui
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

chore: update extended_kv_cache config

Browse Source
This commit is contained in:
jialin
2025-10-31 15:03:23 +08:00
parent f6a3497b0c
commit 2006827968
7 changed files with 74 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/locales/ru-RU/models.ts
+14 -2
View File
@@ -212,7 +212,14 @@ export default {
'Available only with built-in backends (vLLM / SGLang) — switch backend in <span class="bold-text">Advanced</span> to enable.',
'models.form.kvCache.tips2':
'KV cache is only supported when using built-in inference backends (vLLM or SGLang).',
'models.form.scheduling': 'Scheduling'
'models.form.scheduling': 'Scheduling',
'models.form.ramRatio': 'RAM-to-VRAM Ratio',
'models.form.ramSize': 'Maximum RAM Size (GiB)',
'models.form.ramRatio.tips':
'Ratio of system RAM to GPU VRAM used for KV cache. For example, 2.0 means the cache in RAM can be twice as large as the GPU VRAM.',
'models.form.ramSize.tips': `Maximum size of the KV cache stored in system memory (GiB). If set, this value overrides "{content}".`,
'models.form.chunkSize.tips':
'Number of tokens per KV cache chunk. A larger chunk size may improve throughput but increase memory usage.'
};
// ========== To-Do: Translate Keys (Remove After Translation) ==========
@@ -222,5 +229,10 @@ export default {
// 5. 'models.form.remoteURL.tips': 'Refer to the <a href="https://docs.lmcache.ai/api_reference/configurations.html" target="_blank">configuration documentation</a> for details.',
// 6. 'models.form.kvCache.tips': 'Available only with built-in backends (vLLM / SGLang) — switch backend in <span class="bold-text">Advanced</span> to enable.'
// 7. 'models.form.kvCache.tips2': 'KV cache is only supported when using built-in inference backends (vLLM or SGLang).';
// 8. 'models.form.scheduling': 'Scheduling'
// 8. 'models.form.scheduling': 'Scheduling',
// 9. 'models.form.ramRatio': 'RAM-to-VRAM Ratio',
// 10. 'models.form.ramSize': 'Maximum RAM Size (GiB)',
// 11. 'models.form.ramRatio.tips': 'Ratio of system RAM to GPU VRAM used for KV cache. For example, 2.0 means the cache in RAM can be twice as large as the GPU VRAM.',
// 12. 'models.form.ramSize.tips': `Maximum size of the KV cache stored in system memory (GiB). If set, this value overrides "{content}".`,
// 13. 'models.form.chunkSize.tips': 'Number of tokens per KV cache chunk. A larger chunk size may improve throughput but increase memory usage.'
// ========== End of To-Do List ==========