@fugood/buttress-server 2.24.6 → 2.24.7

package/lib/index.mjs

@@ -6,7 +6,7 @@ from huggingface_hub import snapshot_download
 path = snapshot_download("${s}", revision="${o.model.revision||`main`}")
 print(path)
 `.trim(),a={...process.env};o.runtime.huggingface_token&&(a.HF_TOKEN=o.runtime.huggingface_token);let c=await q(t,[`-c`,n],{timeout:6e5,env:a});r?.(1);let u=c.stdout.trim().split(`
-`).pop();i?.({localPath:u,repoId:s,alreadyExists:!1})}catch(e){throw a?.(e),e}finally{t?.deleteDownload(u)}})();return t?.setDownload(u,d),{started:!0,localPath:null,repoId:s}}async function J(e,t=null,n={}){if(e===`ggml-llm`)return vn(t,n);if(e===`ggml-stt`)return ar(t,n);if(e===`mlx-llm`)return zr(t,n);throw Error(`Unknown backend type: ${e}`)}var Y=`@fugood/buttress-backend-core`,X=`2.24.1`,Vr={name:Y,private:!0,type:`module`,version:X,main:`src/index.js`,types:`lib/types/index.d.ts`,scripts:{build:`tsc --noCheck --declaration --emitDeclarationOnly --allowJs --outDir lib/types src/index.js`},dependencies:{"@fugood/buttress-hardware-guardrails":`^2.24.0`,"@fugood/llama.node":`^1.7.4`,"@fugood/whisper.node":`^1.0.19`,"@huggingface/gguf":`^0.3.2`,"@iarna/toml":`^3.0.0`,bytes:`^3.1.0`}};const Hr=e=>{if(!e)return{repoId:null,filename:null};let[t,n]=e.split(`:`);return{repoId:t,filename:n||null}};async function Ur({modelIds:e=[],defaultConfig:t=null}={}){let n=[];console.log(`${Y} v${X}`),console.log(`Generating model capabilities comparison...
+`).pop();i?.({localPath:u,repoId:s,alreadyExists:!1})}catch(e){throw a?.(e),e}finally{t?.deleteDownload(u)}})();return t?.setDownload(u,d),{started:!0,localPath:null,repoId:s}}async function J(e,t=null,n={}){if(e===`ggml-llm`)return vn(t,n);if(e===`ggml-stt`)return ar(t,n);if(e===`mlx-llm`)return zr(t,n);throw Error(`Unknown backend type: ${e}`)}var Y=`@fugood/buttress-backend-core`,X=`2.24.1`,Vr={name:Y,private:!0,type:`module`,version:X,main:`src/index.js`,types:`lib/types/index.d.ts`,scripts:{build:`tsc --noCheck --declaration --emitDeclarationOnly --allowJs --outDir lib/types src/index.js`},dependencies:{"@fugood/buttress-hardware-guardrails":`^2.24.0`,"@fugood/llama.node":`1.7.8`,"@fugood/whisper.node":`^1.0.22`,"@huggingface/gguf":`^0.3.2`,"@iarna/toml":`^3.0.0`,bytes:`^3.1.0`}};const Hr=e=>{if(!e)return{repoId:null,filename:null};let[t,n]=e.split(`:`);return{repoId:t,filename:n||null}};async function Ur({modelIds:e=[],defaultConfig:t=null}={}){let n=[];console.log(`${Y} v${X}`),console.log(`Generating model capabilities comparison...
 `),n.push(`${Y} v${X}`),n.push(`## Model Capabilities Comparison
 `),(!e||e.length===0)&&(console.error(`Error: No model IDs provided`),process.exit(1));try{let r=(e={},t={})=>{let n=Array.isArray(e)?[...e]:{...e};return Object.entries(t||{}).forEach(([e,t])=>{t&&typeof t==`object`&&!Array.isArray(t)?n[e]=r(n[e]||{},t):n[e]=t}),n},{server:i,generators:a=[],...o}=t||{},s=e=>r(structuredClone(o),e||{}),c=e=>{if(Array.isArray(a)&&a.length>0){let t=a.filter(e=>e?.type===`ggml-llm`);if(t.length>0&&e){let n=t.find(t=>t.model?.repo_id===e);if(n)return s(n)}}return Object.keys(o).length>0?s({}):null},u=[];for(let t=0;t<e.length;t+=1){let n=e[t];console.log(`[${t+1}/${e.length}] Analyzing ${n}...`);let r=c(n);r={...r||{},model:{...o.runtime,...r?.model||{},repo_id:n}};let i=await J(`ggml-llm`,null,{config:r,includeBreakdown:!0});u.push({modelId:n,capabilities:i,modelInfo:i.buttress?.selected||null,modelConfig:i.modelConfig||null})}let d=e=>e?(e/1024/1024/1024).toFixed(2):`N/A`,f=e=>e?`✅`:`🚫`;n.push(`| Model ID | Quantization | Size (GB) | Context Size | KV Cache Size (GB) | Total Required Memory (GB) | Fits GPU (Full) | Fits CPU (Full) |`),n.push(`|----------|--------------|-----------|--------------|--------------------|-----------------------------|-----------------|-----------------|`),u.forEach(({modelId:e,modelInfo:t,modelConfig:r})=>{let i=t?.quantization?.name?.toUpperCase()||`N/A`,a=d(t?.modelBytes),o=r?.nCtx||t?.kvInfo?.nCtxTrain||`N/A`,s=qe(t),c=Number(o),l=t?.kvCacheBytes||(s&&Number.isFinite(c)&&c>0?s(c):s&&s(t?.kvInfo?.nCtxTrain||0))||null,u=d(l),p=d(t?.modelBytes&&l?t.modelBytes+l:t?.fit?.totalRequiredBytes),m=f(t?.fit?.fitsInGpu),h=f(t?.fit?.fitsInCpu);n.push(`| ${e} | ${i} | ${a} | ${o} | ${u} | ${p} | ${m} | ${h} |`);let g=t?.memoryLimitedCtx!=null||t?.limitedFit!=null,_=!t?.fit?.fitsInGpu||!t?.fit?.fitsInCpu;if(g&&_){let e=t?.memoryLimitedCtx||o,r=Number(e),i=t?.limitedKvCacheBytes||s&&Number.isFinite(r)&&r>0&&s(r)||null,c=d(i),l=d(t?.modelBytes&&i?t.modelBytes+i:t?.limitedFit?.totalRequiredBytes),m=f(t?.limitedFit?.fitsInGpu),h=f(t?.limitedFit?.fitsInCpu);(e!==o||c!==u||l!==p)&&n.push(`| ↳ Limited | - | ${a} | ${e} | ${c} | ${l} | ${m} | ${h} |`)}}),n.push(`
 ---`),n.push(`

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@fugood/buttress-server",
-  "version": "2.24.6",
+  "version": "2.24.7",
   "main": "lib/index.mjs",
   "types": "lib/index.d.mts",
   "type": "module",
@@ -30,8 +30,8 @@
   "dependencies": {
     "@elysiajs/cors": "^1.1.1",
     "@elysiajs/node": "^1.4.2",
-    "@fugood/llama.node": "^1.7.4",
-    "@fugood/whisper.node": "^1.0.19",
+    "@fugood/llama.node": "1.7.8",
+    "@fugood/whisper.node": "^1.0.22",
     "@huggingface/gguf": "^0.3.2",
     "@iarna/toml": "^3.0.0",
     "bytes": "^3.1.0",