mirror of
https://github.com/zenlm/zen-blog.git
synced 2026-11-02 17:28:53 +00:00
98 lines
54 KiB
Plaintext
98 lines
54 KiB
Plaintext
1:"$Sreact.fragment"
|
||
2:I[106,["/_next/static/chunks/59d0ad1b64f8544e.js"],"RootProvider"]
|
||
3:I[53113,["/_next/static/chunks/4d80e004cf4896dd.js","/_next/static/chunks/350ee4303b732916.js"],"default"]
|
||
4:I[73211,["/_next/static/chunks/4d80e004cf4896dd.js","/_next/static/chunks/350ee4303b732916.js"],"default"]
|
||
5:I[10086,["/_next/static/chunks/59d0ad1b64f8544e.js","/_next/static/chunks/8de849ca74fc071f.js","/_next/static/chunks/e62b91212ee7f8ff.js","/_next/static/chunks/f19fe44237e54646.js","/_next/static/chunks/cb0a883bafeb6805.js"],""]
|
||
7:I[89923,["/_next/static/chunks/4d80e004cf4896dd.js","/_next/static/chunks/350ee4303b732916.js"],"OutletBoundary"]
|
||
8:"$Sreact.suspense"
|
||
a:I[89923,["/_next/static/chunks/4d80e004cf4896dd.js","/_next/static/chunks/350ee4303b732916.js"],"ViewportBoundary"]
|
||
c:I[89923,["/_next/static/chunks/4d80e004cf4896dd.js","/_next/static/chunks/350ee4303b732916.js"],"MetadataBoundary"]
|
||
e:I[6998,["/_next/static/chunks/4d80e004cf4896dd.js","/_next/static/chunks/350ee4303b732916.js"],"default"]
|
||
:HL["/_next/static/chunks/f2332aac77592f9d.css","style"]
|
||
0:{"P":null,"b":"i-dnJM_MIpJSOCQWNJVMq","c":["","blog","bitdelta-behavioral-compression"],"q":"","i":false,"f":[[["",{"children":["blog",{"children":[["slug","bitdelta-behavioral-compression","d"],{"children":["__PAGE__",{}]}]}]},"$undefined","$undefined",true],[["$","$1","c",{"children":[[["$","link","0",{"rel":"stylesheet","href":"/_next/static/chunks/f2332aac77592f9d.css","precedence":"next","crossOrigin":"$undefined","nonce":"$undefined"}],["$","script","script-0",{"src":"/_next/static/chunks/59d0ad1b64f8544e.js","async":true,"nonce":"$undefined"}]],["$","html",null,{"lang":"en","className":"dark","suppressHydrationWarning":true,"children":["$","body",null,{"className":"antialiased","children":["$","$L2",null,{"children":["$","$L3",null,{"parallelRouterKey":"children","error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L4",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","main",null,{"className":"flex min-h-screen flex-col items-center justify-center px-4 text-center","children":[["$","div",null,{"className":"mb-8 opacity-20","children":["$","svg",null,{"width":"120","height":"120","viewBox":"0 0 120 120","fill":"none","aria-hidden":"true","children":["$","circle",null,{"cx":"60","cy":"60","r":"50","stroke":"currentColor","strokeWidth":"3","strokeLinecap":"round","strokeDasharray":"280 40"}]}]}],["$","p",null,{"className":"text-xs font-mono uppercase tracking-[0.3em] text-fd-muted-foreground mb-4","children":"404"}],["$","h1",null,{"className":"text-3xl font-semibold mb-3","children":"Page not found"}],["$","p",null,{"className":"text-fd-muted-foreground max-w-sm mb-10","children":"This page doesn't exist, or it may have moved. Try the documentation or head home."}],["$","div",null,{"className":"flex flex-wrap gap-3 justify-center","children":[["$","$L5",null,{"href":"/","className":"inline-flex items-center gap-2 rounded-lg bg-fd-primary text-fd-primary-foreground px-4 py-2 text-sm font-medium hover:opacity-90 transition","children":"Go home"}],["$","$L5",null,{"href":"/docs","className":"inline-flex items-center gap-2 rounded-lg border border-fd-border bg-fd-background px-4 py-2 text-sm font-medium hover:bg-fd-muted transition","children":"Documentation"}],["$","$L5",null,{"href":"/docs/models","className":"inline-flex items-center gap-2 rounded-lg border border-fd-border bg-fd-background px-4 py-2 text-sm font-medium hover:bg-fd-muted transition","children":"Browse models"}]]}],["$","p",null,{"className":"mt-16 text-xs font-mono text-fd-muted-foreground opacity-50","children":"zenlm.org"}]]}],[]],"forbidden":"$undefined","unauthorized":"$undefined"}]}]}]}]]}],{"children":[["$","$1","c",{"children":[null,["$","$L3",null,{"parallelRouterKey":"children","error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L4",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","forbidden":"$undefined","unauthorized":"$undefined"}]]}],{"children":[["$","$1","c",{"children":[null,["$","$L3",null,{"parallelRouterKey":"children","error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L4",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","forbidden":"$undefined","unauthorized":"$undefined"}]]}],{"children":[["$","$1","c",{"children":["$L6",[["$","script","script-0",{"src":"/_next/static/chunks/8de849ca74fc071f.js","async":true,"nonce":"$undefined"}],["$","script","script-1",{"src":"/_next/static/chunks/e62b91212ee7f8ff.js","async":true,"nonce":"$undefined"}],["$","script","script-2",{"src":"/_next/static/chunks/f19fe44237e54646.js","async":true,"nonce":"$undefined"}],["$","script","script-3",{"src":"/_next/static/chunks/cb0a883bafeb6805.js","async":true,"nonce":"$undefined"}]],["$","$L7",null,{"children":["$","$8",null,{"name":"Next.MetadataOutlet","children":"$@9"}]}]]}],{},null,false,false]},null,false,false]},null,false,false]},null,false,false],["$","$1","h",{"children":[null,["$","$La",null,{"children":"$Lb"}],["$","div",null,{"hidden":true,"children":["$","$Lc",null,{"children":["$","$8",null,{"name":"Next.Metadata","children":"$Ld"}]}]}],null]}],false]],"m":"$undefined","G":["$e",[]],"S":true}
|
||
f:I[48068,["/_next/static/chunks/59d0ad1b64f8544e.js","/_next/static/chunks/8de849ca74fc071f.js","/_next/static/chunks/e62b91212ee7f8ff.js","/_next/static/chunks/f19fe44237e54646.js","/_next/static/chunks/cb0a883bafeb6805.js"],"default"]
|
||
6:["$","main",null,{"className":"mx-auto w-full max-w-2xl px-4 py-16","children":[["$","$L5",null,{"href":"/blog","className":"inline-flex items-center gap-1.5 text-sm text-fd-muted-foreground hover:text-fd-foreground mb-10 transition-colors","children":"← Back to Blog"}],["$","div",null,{"className":"mb-8","children":[["$","time",null,{"className":"text-xs font-mono text-fd-muted-foreground uppercase tracking-wider","children":"February 27, 2026"}],["$","h1",null,{"className":"text-3xl font-bold mt-2 mb-3","children":"BitDelta: 1-Bit Behavioral Compression Across the Zen Model Family"}],["$","p",null,{"className":"text-fd-muted-foreground text-lg mb-4","children":"How BitDelta (arXiv:2402.10193) compresses fine-tuned behavioral deltas to 1-bit precision, enabling the full Zen model family — nano through ultra — to share a single GPU cluster."}],["$","div",null,{"className":"flex items-center gap-3 pt-4 border-t border-fd-border","children":[["$","span",null,{"className":"text-sm text-fd-muted-foreground","children":["By ","Zen LM Team"]}],["$","div",null,{"className":"flex gap-1.5 ml-auto","children":[["$","span","Research",{"className":"text-[10px] font-mono uppercase tracking-wider bg-fd-muted text-fd-muted-foreground px-1.5 py-0.5 rounded","children":"Research"}],["$","span","Quantization",{"className":"text-[10px] font-mono uppercase tracking-wider bg-fd-muted text-fd-muted-foreground px-1.5 py-0.5 rounded","children":"Quantization"}],["$","span","BitDelta",{"className":"text-[10px] font-mono uppercase tracking-wider bg-fd-muted text-fd-muted-foreground px-1.5 py-0.5 rounded","children":"BitDelta"}],["$","span","Model Serving",{"className":"text-[10px] font-mono uppercase tracking-wider bg-fd-muted text-fd-muted-foreground px-1.5 py-0.5 rounded","children":"Model Serving"}],["$","span","Delta Compression",{"className":"text-[10px] font-mono uppercase tracking-wider bg-fd-muted text-fd-muted-foreground px-1.5 py-0.5 rounded","children":"Delta Compression"}]]}]]}]]}],["$","div",null,{"className":"prose dark:prose-invert max-w-none","children":[["$","p",null,{"children":[["$","$Lf",null,{"href":"https://arxiv.org/abs/2402.10193","children":"BITDELTA PAPER"}]," ",["$","$Lf",null,{"href":"https://arxiv.org/abs/2602.09689","children":"MONOSOUP PAPER"}]," ",["$","$Lf",null,{"href":"https://arxiv.org/abs/2510.13537","children":"K-MERGE PAPER"}]," ",["$","$Lf",null,{"href":"https://huggingface.co/zenlm","children":"ZEN MODELS"}]]}],"\n",["$","p",null,{"children":"The Zen model family has a deployment problem that is not immediately obvious from the outside. We publish 14+ distinct model variants — from zen-nano at 0.6B parameters to zen4-ultra at 1.04T. Each variant carries fine-tuned behavioral characteristics: different personas, different task specializations, different safety postures. In a naive serving architecture, each variant is a separate set of weights. Loading all of them onto a GPU cluster is economically impossible."}],"\n",["$","p",null,{"children":"BitDelta is how we solve this. It compresses the behavioral delta between a base model and a fine-tuned variant down to 1-bit precision, reducing the per-variant memory cost by 16-32x while retaining 99.3% of full-precision behavioral accuracy."}],"\n",["$","h2",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"the-multi-variant-deployment-problem","children":[["$","a",null,{"data-card":"","href":"#the-multi-variant-deployment-problem","className":"peer","children":"The Multi-Variant Deployment Problem"}],["$","svg",null,{"ref":"$undefined","xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100","aria-hidden":true,"children":["$L10","$L11","$undefined"]}]]}],"\n","$L12","\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n","$L13","\n","$L14","\n","$L15","\n","$L16","\n","$L17","\n","$L18","\n","$L19","\n","$L1a","\n","$L1b","\n","$L1c","\n","$L1d","\n","$L1e","\n","$L1f","\n","$L20","\n","$L21","\n","$L22","\n","$L23","\n","$L24","\n","$L25","\n","$L26","\n","$L27","\n","$L28","\n","$L29","\n","$L2a","\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n","$L2b","\n","$L2c","\n","$L2d","\n","$L2e","\n","$L2f","\n","$L30","\n","$L31","\n","$L32","\n","$L33","\n","$L34","\n","$L35","\n","$L36","\n","$L37","\n","$L38","\n","$L39","\n","$L3a","\n","$L3b","\n","$L3c","\n","$L3d","\n","$L3e","\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n","$L3f","\n","$L40","\n","$L41","\n","$L42","\n","$L43"]}]]}]
|
||
44:I[51504,["/_next/static/chunks/59d0ad1b64f8544e.js","/_next/static/chunks/8de849ca74fc071f.js","/_next/static/chunks/e62b91212ee7f8ff.js","/_next/static/chunks/f19fe44237e54646.js","/_next/static/chunks/cb0a883bafeb6805.js"],"CodeBlock"]
|
||
45:I[51504,["/_next/static/chunks/59d0ad1b64f8544e.js","/_next/static/chunks/8de849ca74fc071f.js","/_next/static/chunks/e62b91212ee7f8ff.js","/_next/static/chunks/f19fe44237e54646.js","/_next/static/chunks/cb0a883bafeb6805.js"],"Pre"]
|
||
10:["$","path","1cjeqo",{"d":"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"}]
|
||
11:["$","path","19qd67",{"d":"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"}]
|
||
12:["$","p",null,{"children":"Consider the economics concretely. A single zen4-ultra shard (1.04T parameters, bfloat16) requires roughly 2TB of GPU memory. Even a single full-precision variant of zen-max (72B) requires ~144GB. With 14 variants across our model catalog:"}]
|
||
13:["$","div",null,{"className":"relative overflow-auto prose-no-margin my-6","children":["$","table",null,{"children":[["$","thead",null,{"children":["$","tr",null,{"children":[["$","th",null,{"children":"Tier"}],["$","th",null,{"children":"Parameters"}],["$","th",null,{"children":"Full Precision (BF16)"}],["$","th",null,{"children":"Variants"}],["$","th",null,{"children":"Total"}]]}]}],["$","tbody",null,{"children":[["$","tr",null,{"children":[["$","td",null,{"children":"nano"}],["$","td",null,{"children":"0.6B"}],["$","td",null,{"children":"1.2 GB"}],["$","td",null,{"children":"4"}],["$","td",null,{"children":"4.8 GB"}]]}],["$","tr",null,{"children":[["$","td",null,{"children":"eco / coder-4b"}],["$","td",null,{"children":"4B"}],["$","td",null,{"children":"8 GB"}],["$","td",null,{"children":"3"}],["$","td",null,{"children":"24 GB"}]]}],["$","tr",null,{"children":[["$","td",null,{"children":"zen4-max"}],["$","td",null,{"children":"30B"}],["$","td",null,{"children":"60 GB"}],["$","td",null,{"children":"3"}],["$","td",null,{"children":"180 GB"}]]}],["$","tr",null,{"children":[["$","td",null,{"children":"zen-max"}],["$","td",null,{"children":"72B"}],["$","td",null,{"children":"144 GB"}],["$","td",null,{"children":"2"}],["$","td",null,{"children":"288 GB"}]]}],["$","tr",null,{"children":[["$","td",null,{"children":"zen4-ultra"}],["$","td",null,{"children":"1.04T"}],["$","td",null,{"children":"~2 TB"}],["$","td",null,{"children":"1"}],["$","td",null,{"children":"~2 TB"}]]}]]}]]}]}]
|
||
14:["$","p",null,{"children":"Keeping all of these “hot” simultaneously is not feasible. Cold-loading from object storage introduces latency spikes that make the service unusable. We need a different architecture."}]
|
||
15:["$","p",null,{"children":["The key observation: most variants share an identical base model. The behavioral differences — the fine-tuned identity, the task specialization, the adjusted refusal boundaries — live in the ",["$","strong",null,{"children":"delta"}]," between fine-tuned weights and base weights. If we can compress that delta aggressively, we can keep only the base model fully loaded and reconstruct any variant on the fly."]}]
|
||
16:["$","h2",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"bitdelta-theory","children":[["$","a",null,{"data-card":"","href":"#bitdelta-theory","className":"peer","children":"BitDelta Theory"}],["$","svg",null,{"ref":"$undefined","xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100","aria-hidden":true,"children":[["$","path","1cjeqo",{"d":"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"}],["$","path","19qd67",{"d":"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"}],"$undefined"]}]]}]
|
||
17:["$","p",null,{"children":[["$","strong",null,{"children":"Paper"}]," : arXiv:2402.10193"]}]
|
||
18:["$","p",null,{"children":"BitDelta decomposes a fine-tuned weight matrix as:"}]
|
||
19:["$","$L44",null,{"className":"shiki shiki-themes github-light github-dark","style":{"--shiki-light":"#24292e","--shiki-dark":"#e1e4e8","--shiki-light-bg":"#fff","--shiki-dark-bg":"#24292e"},"tabIndex":"0","icon":"<svg viewBox=\"0 0 24 24\"><path d=\"M 6,1 C 4.354992,1 3,2.354992 3,4 v 16 c 0,1.645008 1.354992,3 3,3 h 12 c 1.645008,0 3,-1.354992 3,-3 V 8 7 A 1.0001,1.0001 0 0 0 20.707031,6.2929687 l -5,-5 A 1.0001,1.0001 0 0 0 15,1 h -1 z m 0,2 h 7 v 3 c 0,1.645008 1.354992,3 3,3 h 3 v 11 c 0,0.564129 -0.435871,1 -1,1 H 6 C 5.4358712,21 5,20.564129 5,20 V 4 C 5,3.4358712 5.4358712,3 6,3 Z M 15,3.4140625 18.585937,7 H 16 C 15.435871,7 15,6.5641288 15,6 Z\" fill=\"currentColor\" /></svg>","children":["$","$L45",null,{"children":["$","code",null,{"children":[["$","span",null,{"className":"line","children":["$","span",null,{}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" W_ft = W_base + Δ"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" "}]}]]}]}]}]
|
||
1a:["$","p",null,{"children":"and approximates the delta with 1-bit quantization:"}]
|
||
1b:["$","$L44",null,{"className":"shiki shiki-themes github-light github-dark","style":{"--shiki-light":"#24292e","--shiki-dark":"#e1e4e8","--shiki-light-bg":"#fff","--shiki-dark-bg":"#24292e"},"tabIndex":"0","icon":"<svg viewBox=\"0 0 24 24\"><path d=\"M 6,1 C 4.354992,1 3,2.354992 3,4 v 16 c 0,1.645008 1.354992,3 3,3 h 12 c 1.645008,0 3,-1.354992 3,-3 V 8 7 A 1.0001,1.0001 0 0 0 20.707031,6.2929687 l -5,-5 A 1.0001,1.0001 0 0 0 15,1 h -1 z m 0,2 h 7 v 3 c 0,1.645008 1.354992,3 3,3 h 3 v 11 c 0,0.564129 -0.435871,1 -1,1 H 6 C 5.4358712,21 5,20.564129 5,20 V 4 C 5,3.4358712 5.4358712,3 6,3 Z M 15,3.4140625 18.585937,7 H 16 C 15.435871,7 15,6.5641288 15,6 Z\" fill=\"currentColor\" /></svg>","children":["$","$L45",null,{"children":["$","code",null,{"children":[["$","span",null,{"className":"line","children":["$","span",null,{}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" Δ ≈ α · sign(Δ)"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" "}]}]]}]}]}]
|
||
1c:["$","p",null,{"children":"where the scale factor α is the mean absolute value of the delta entries:"}]
|
||
1d:["$","$L44",null,{"className":"shiki shiki-themes github-light github-dark","style":{"--shiki-light":"#24292e","--shiki-dark":"#e1e4e8","--shiki-light-bg":"#fff","--shiki-dark-bg":"#24292e"},"tabIndex":"0","icon":"<svg viewBox=\"0 0 24 24\"><path d=\"M 6,1 C 4.354992,1 3,2.354992 3,4 v 16 c 0,1.645008 1.354992,3 3,3 h 12 c 1.645008,0 3,-1.354992 3,-3 V 8 7 A 1.0001,1.0001 0 0 0 20.707031,6.2929687 l -5,-5 A 1.0001,1.0001 0 0 0 15,1 h -1 z m 0,2 h 7 v 3 c 0,1.645008 1.354992,3 3,3 h 3 v 11 c 0,0.564129 -0.435871,1 -1,1 H 6 C 5.4358712,21 5,20.564129 5,20 V 4 C 5,3.4358712 5.4358712,3 6,3 Z M 15,3.4140625 18.585937,7 H 16 C 15.435871,7 15,6.5641288 15,6 Z\" fill=\"currentColor\" /></svg>","children":["$","$L45",null,{"children":["$","code",null,{"children":[["$","span",null,{"className":"line","children":["$","span",null,{}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" α = (1/n) Σ |Δ_ij|"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" "}]}]]}]}]}]
|
||
1e:["$","p",null,{"children":"This is a single scalar per weight matrix. The sign matrix is 1-bit per element. Total storage for the delta: n bits + 1 float32. For a 4096×4096 weight matrix, that is 16MB → 2MB. For the full zen-max 72B delta, the storage requirement drops from ~144GB to ~9GB."}]
|
||
1f:["$","p",null,{"children":"Why does 1-bit sign quantization work? The delta values in fine-tuned LLMs follow a near-Laplace distribution centered at zero. The signs carry the directional information; the scale α captures the magnitude. The residual error:"}]
|
||
20:["$","$L44",null,{"className":"shiki shiki-themes github-light github-dark","style":{"--shiki-light":"#24292e","--shiki-dark":"#e1e4e8","--shiki-light-bg":"#fff","--shiki-dark-bg":"#24292e"},"tabIndex":"0","icon":"<svg viewBox=\"0 0 24 24\"><path d=\"M 6,1 C 4.354992,1 3,2.354992 3,4 v 16 c 0,1.645008 1.354992,3 3,3 h 12 c 1.645008,0 3,-1.354992 3,-3 V 8 7 A 1.0001,1.0001 0 0 0 20.707031,6.2929687 l -5,-5 A 1.0001,1.0001 0 0 0 15,1 h -1 z m 0,2 h 7 v 3 c 0,1.645008 1.354992,3 3,3 h 3 v 11 c 0,0.564129 -0.435871,1 -1,1 H 6 C 5.4358712,21 5,20.564129 5,20 V 4 C 5,3.4358712 5.4358712,3 6,3 Z M 15,3.4140625 18.585937,7 H 16 C 15.435871,7 15,6.5641288 15,6 Z\" fill=\"currentColor\" /></svg>","children":["$","$L45",null,{"children":["$","code",null,{"children":[["$","span",null,{"className":"line","children":["$","span",null,{}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" ε = Δ - α · sign(Δ)"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" "}]}]]}]}]}]
|
||
21:["$","p",null,{"children":"has bounded expected squared norm:"}]
|
||
22:["$","$L44",null,{"className":"shiki shiki-themes github-light github-dark","style":{"--shiki-light":"#24292e","--shiki-dark":"#e1e4e8","--shiki-light-bg":"#fff","--shiki-dark-bg":"#24292e"},"tabIndex":"0","icon":"<svg viewBox=\"0 0 24 24\"><path d=\"M 6,1 C 4.354992,1 3,2.354992 3,4 v 16 c 0,1.645008 1.354992,3 3,3 h 12 c 1.645008,0 3,-1.354992 3,-3 V 8 7 A 1.0001,1.0001 0 0 0 20.707031,6.2929687 l -5,-5 A 1.0001,1.0001 0 0 0 15,1 h -1 z m 0,2 h 7 v 3 c 0,1.645008 1.354992,3 3,3 h 3 v 11 c 0,0.564129 -0.435871,1 -1,1 H 6 C 5.4358712,21 5,20.564129 5,20 V 4 C 5,3.4358712 5.4358712,3 6,3 Z M 15,3.4140625 18.585937,7 H 16 C 15.435871,7 15,6.5641288 15,6 Z\" fill=\"currentColor\" /></svg>","children":["$","$L45",null,{"children":["$","code",null,{"children":[["$","span",null,{"className":"line","children":["$","span",null,{}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" E[||ε||²] ≤ (1 - 2/π) · ||Δ||² ≈ 0.36 · ||Δ||²"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" "}]}]]}]}]}]
|
||
23:["$","p",null,{"children":"In practice (and this is the empirical surprise), the effective error on model outputs is far smaller than this bound suggests, because the residuals are uncorrelated with the task-relevant signal directions. The model’s behavioral accuracy degrades gracefully rather than catastrophically."}]
|
||
24:["$","h2",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"implementation-fused-cuda-kernel","children":[["$","a",null,{"data-card":"","href":"#implementation-fused-cuda-kernel","className":"peer","children":"Implementation: Fused CUDA Kernel"}],["$","svg",null,{"ref":"$undefined","xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100","aria-hidden":true,"children":[["$","path","1cjeqo",{"d":"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"}],["$","path","19qd67",{"d":"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"}],"$undefined"]}]]}]
|
||
25:["$","p",null,{"children":["The critical implementation detail is efficiency. Reconstructing ",["$","code",null,{"children":"W_ft = W_base + α · sign(Δ)"}]," at inference time must not add meaningful latency. Our CUDA kernel fuses three operations:"]}]
|
||
26:["$","ol",null,{"children":["\n",["$","li",null,{"children":"Load sign bits from compressed storage (1-bit tensor, integer packing)"}],"\n",["$","li",null,{"children":["Unpack and scale: ",["$","code",null,{"children":"delta_row = alpha * sign_bits.float() * 2 - 1"}]]}],"\n",["$","li",null,{"children":"Add to base weight tile in shared memory before GEMM"}],"\n"]}]
|
||
27:["$","p",null,{"children":"The result: delta reconstruction adds less than 1ms overhead per forward pass on an A100. In practice the overhead is dominated by memory bandwidth to load the sign bits, which at 1/16th the size of the base weight tensor is negligible."}]
|
||
46:T5c0,<svg viewBox="0 0 24 24"><path d="M14.25.18l.9.2.73.26.59.3.45.32.34.34.25.34.16.33.1.3.04.26.02.2-.01.13V8.5l-.05.63-.13.55-.21.46-.26.38-.3.31-.33.25-.35.19-.35.14-.33.1-.3.07-.26.04-.21.02H8.77l-.69.05-.59.14-.5.22-.41.27-.33.32-.27.35-.2.36-.15.37-.1.35-.07.32-.04.27-.02.21v3.06H3.17l-.21-.03-.28-.07-.32-.12-.35-.18-.36-.26-.36-.36-.35-.46-.32-.59-.28-.73-.21-.88-.14-1.05-.05-1.23.06-1.22.16-1.04.24-.87.32-.71.36-.57.4-.44.42-.33.42-.24.4-.16.36-.1.32-.05.24-.01h.16l.06.01h8.16v-.83H6.18l-.01-2.75-.02-.37.05-.34.11-.31.17-.28.25-.26.31-.23.38-.2.44-.18.51-.15.58-.12.64-.1.71-.06.77-.04.84-.02 1.27.05zm-6.3 1.98l-.23.33-.08.41.08.41.23.34.33.22.41.09.41-.09.33-.22.23-.34.08-.41-.08-.41-.23-.33-.33-.22-.41-.09-.41.09zm13.09 3.95l.28.06.32.12.35.18.36.27.36.35.35.47.32.59.28.73.21.88.14 1.04.05 1.23-.06 1.23-.16 1.04-.24.86-.32.71-.36.57-.4.45-.42.33-.42.24-.4.16-.36.09-.32.05-.24.02-.16-.01h-8.22v.82h5.84l.01 2.76.02.36-.05.34-.11.31-.17.29-.25.25-.31.24-.38.2-.44.17-.51.15-.58.13-.64.09-.71.07-.77.04-.84.01-1.27-.04-1.07-.14-.9-.2-.73-.25-.59-.3-.45-.33-.34-.34-.25-.34-.16-.33-.1-.3-.04-.25-.02-.2.01-.13v-5.34l.05-.64.13-.54.21-.46.26-.38.3-.32.33-.24.35-.2.35-.14.33-.1.3-.06.26-.04.21-.02.13-.01h5.84l.69-.05.59-.14.5-.21.41-.28.33-.32.27-.35.2-.36.15-.36.1-.35.07-.32.04-.28.02-.21V6.07h2.09l.14.01zm-6.47 14.25l-.23.33-.08.41.08.41.23.33.33.23.41.08.41-.08.33-.23.23-.33.08-.41-.08-.41-.23-.33-.33-.23-.41-.08-.41.08z" fill="currentColor" /></svg>28:["$","$L44",null,{"className":"shiki shiki-themes github-light github-dark","style":{"--shiki-light":"#24292e","--shiki-dark":"#e1e4e8","--shiki-light-bg":"#fff","--shiki-dark-bg":"#24292e"},"tabIndex":"0","icon":"$46","children":["$","$L45",null,{"children":["$","code",null,{"children":[["$","span",null,{"className":"line"}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" import"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" torch"}]]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" def"}],["$","span",null,{"style":{"--shiki-light":"#6F42C1","--shiki-dark":"#B392F0"},"children":" compress_delta"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":"(W_ft: torch.Tensor, W_base: torch.Tensor) -> tuple[torch.Tensor, torch.Tensor]:"}]]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":" \"\"\"Compress fine-tuned weight delta to 1-bit + scale.\"\"\""}]}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" delta "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" W_ft "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"-"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" W_base"}]]}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" alpha "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" delta.abs().mean()"}]]}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" sign_bits "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],"$L47","$L48","$L49","$L4a","$L4b"]}],"\n","$L4c","\n","$L4d","\n","$L4e","\n","$L4f","\n","$L50","\n","$L51","\n","$L52","\n","$L53","\n","$L54","\n","$L55","\n","$L56","\n","$L57","\n","$L58","\n","$L59","\n","$L5a","\n","$L5b","\n","$L5c"]}]}]}]
|
||
29:["$","h2",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"quality-results","children":[["$","a",null,{"data-card":"","href":"#quality-results","className":"peer","children":"Quality Results"}],["$","svg",null,{"ref":"$undefined","xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100","aria-hidden":true,"children":[["$","path","1cjeqo",{"d":"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"}],["$","path","19qd67",{"d":"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"}],"$undefined"]}]]}]
|
||
2a:["$","p",null,{"children":"We evaluated BitDelta across five Zen variants against their full-precision counterparts:"}]
|
||
2b:["$","div",null,{"className":"relative overflow-auto prose-no-margin my-6","children":["$","table",null,{"children":[["$","thead",null,{"children":["$","tr",null,{"children":[["$","th",null,{"children":"Model"}],["$","th",null,{"children":"Task"}],["$","th",null,{"children":"Full Precision"}],["$","th",null,{"children":"BitDelta"}],["$","th",null,{"children":"Retention"}]]}]}],["$","tbody",null,{"children":[["$","tr",null,{"children":[["$","td",null,{"children":"zen-nano"}],["$","td",null,{"children":"MMLU"}],["$","td",null,{"children":"61.3"}],["$","td",null,{"children":"60.8"}],["$","td",null,{"children":"99.2%"}]]}],["$","tr",null,{"children":[["$","td",null,{"children":"zen4-max"}],["$","td",null,{"children":"HumanEval"}],["$","td",null,{"children":"74.1"}],["$","td",null,{"children":"73.5"}],["$","td",null,{"children":"99.1%"}]]}],["$","tr",null,{"children":[["$","td",null,{"children":"zen4-pro"}],["$","td",null,{"children":"GSM8K"}],["$","td",null,{"children":"88.4"}],["$","td",null,{"children":"87.9"}],["$","td",null,{"children":"99.4%"}]]}],["$","tr",null,{"children":[["$","td",null,{"children":"zen-max"}],["$","td",null,{"children":"GPQA"}],["$","td",null,{"children":"71.2"}],["$","td",null,{"children":"70.6"}],["$","td",null,{"children":"99.2%"}]]}],["$","tr",null,{"children":[["$","td",null,{"children":"zen4-ultra"}],["$","td",null,{"children":"AIME 2024"}],["$","td",null,{"children":"94.7"}],["$","td",null,{"children":"93.6"}],["$","td",null,{"children":"98.8%"}]]}]]}]]}]}]
|
||
2c:["$","p",null,{"children":["Average behavioral retention: ",["$","strong",null,{"children":"99.3%"}],". The 0.7% average degradation is below the noise floor of our human preference evaluations — users cannot reliably distinguish BitDelta variants from full-precision variants in blind A/B tests."]}]
|
||
2d:["$","h2",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"monosoup-svd-fallback-for-weak-checkpoints","children":[["$","a",null,{"data-card":"","href":"#monosoup-svd-fallback-for-weak-checkpoints","className":"peer","children":"MonoSoup: SVD Fallback for Weak Checkpoints"}],["$","svg",null,{"ref":"$undefined","xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100","aria-hidden":true,"children":[["$","path","1cjeqo",{"d":"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"}],["$","path","19qd67",{"d":"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"}],"$undefined"]}]]}]
|
||
2e:["$","p",null,{"children":[["$","strong",null,{"children":"Paper"}]," : arXiv:2602.09689"]}]
|
||
2f:["$","p",null,{"children":"BitDelta works well when the delta is well-behaved (small, distributed, near-Laplace). Some fine-tuned checkpoints — particularly those from aggressive few-shot fine-tuning or noisy datasets — produce deltas that are large and spiky. In these cases, 1-bit quantization introduces perceptible degradation."}]
|
||
30:["$","p",null,{"children":"MonoSoup provides a complementary approach: instead of compressing the delta, decompose the full fine-tuned weight via SVD and keep only the top-k singular triplets:"}]
|
||
31:["$","$L44",null,{"className":"shiki shiki-themes github-light github-dark","style":{"--shiki-light":"#24292e","--shiki-dark":"#e1e4e8","--shiki-light-bg":"#fff","--shiki-dark-bg":"#24292e"},"tabIndex":"0","icon":"<svg viewBox=\"0 0 24 24\"><path d=\"M 6,1 C 4.354992,1 3,2.354992 3,4 v 16 c 0,1.645008 1.354992,3 3,3 h 12 c 1.645008,0 3,-1.354992 3,-3 V 8 7 A 1.0001,1.0001 0 0 0 20.707031,6.2929687 l -5,-5 A 1.0001,1.0001 0 0 0 15,1 h -1 z m 0,2 h 7 v 3 c 0,1.645008 1.354992,3 3,3 h 3 v 11 c 0,0.564129 -0.435871,1 -1,1 H 6 C 5.4358712,21 5,20.564129 5,20 V 4 C 5,3.4358712 5.4358712,3 6,3 Z M 15,3.4140625 18.585937,7 H 16 C 15.435871,7 15,6.5641288 15,6 Z\" fill=\"currentColor\" /></svg>","children":["$","$L45",null,{"children":["$","code",null,{"children":[["$","span",null,{"className":"line","children":["$","span",null,{}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" W_ft ≈ U_k Σ_k V_k^T"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" "}]}]]}]}]}]
|
||
32:["$","p",null,{"children":"where k is chosen to keep 95% of the Frobenius norm. This is not a delta compression technique — it operates on the single fine-tuned checkpoint directly. But for weak checkpoints where BitDelta degrades, MonoSoup recovers up to 8% of the lost behavioral accuracy at comparable memory cost."}]
|
||
33:["$","p",null,{"children":"In our pipeline: we try BitDelta first. If behavioral retention falls below 98.5% on our internal benchmark suite, we fall back to MonoSoup with k calibrated to budget."}]
|
||
34:["$","h2",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"k-merge-edge-adapter-management","children":[["$","a",null,{"data-card":"","href":"#k-merge-edge-adapter-management","className":"peer","children":"K-Merge: Edge Adapter Management"}],["$","svg",null,{"ref":"$undefined","xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100","aria-hidden":true,"children":[["$","path","1cjeqo",{"d":"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"}],["$","path","19qd67",{"d":"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"}],"$undefined"]}]]}]
|
||
35:["$","p",null,{"children":[["$","strong",null,{"children":"Paper"}]," : arXiv:2510.13537"]}]
|
||
36:["$","p",null,{"children":"The cloud serving stack above does not address edge deployment. A local user running zen-nano on a 16GB laptop cannot afford a delta cache for 14 variants — even at 1-bit compression, storing all nano variants would consume significant RAM."}]
|
||
37:["$","p",null,{"children":["K-Merge addresses this with an ",["$","strong",null,{"children":"online LoRA adapter pool under fixed storage budget"}],". The algorithm maintains a priority queue of adapters scored by utility:"]}]
|
||
38:["$","$L44",null,{"className":"shiki shiki-themes github-light github-dark","style":{"--shiki-light":"#24292e","--shiki-dark":"#e1e4e8","--shiki-light-bg":"#fff","--shiki-dark-bg":"#24292e"},"tabIndex":"0","icon":"<svg viewBox=\"0 0 24 24\"><path d=\"M 6,1 C 4.354992,1 3,2.354992 3,4 v 16 c 0,1.645008 1.354992,3 3,3 h 12 c 1.645008,0 3,-1.354992 3,-3 V 8 7 A 1.0001,1.0001 0 0 0 20.707031,6.2929687 l -5,-5 A 1.0001,1.0001 0 0 0 15,1 h -1 z m 0,2 h 7 v 3 c 0,1.645008 1.354992,3 3,3 h 3 v 11 c 0,0.564129 -0.435871,1 -1,1 H 6 C 5.4358712,21 5,20.564129 5,20 V 4 C 5,3.4358712 5.4358712,3 6,3 Z M 15,3.4140625 18.585937,7 H 16 C 15.435871,7 15,6.5641288 15,6 Z\" fill=\"currentColor\" /></svg>","children":["$","$L45",null,{"children":["$","code",null,{"children":[["$","span",null,{"className":"line","children":["$","span",null,{}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" utility(adapter_i) = request_frequency(i) × behavioral_gain(i) / storage_cost(i)"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" "}]}]]}]}]}]
|
||
39:["$","p",null,{"children":"When the budget is exceeded, the lowest-utility adapter is evicted. Utility scores are updated online using exponential decay, so recently used adapters are preferred over historical ones."}]
|
||
3a:["$","p",null,{"children":"For a 16GB laptop with 4GB allocated to the adapter pool, K-Merge keeps 6-8 zen-nano variants hot simultaneously, with eviction latency of ~200ms to load a new adapter from local disk."}]
|
||
3b:["$","h2",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"full-zen-serving-stack","children":[["$","a",null,{"data-card":"","href":"#full-zen-serving-stack","className":"peer","children":"Full Zen Serving Stack"}],["$","svg",null,{"ref":"$undefined","xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100","aria-hidden":true,"children":[["$","path","1cjeqo",{"d":"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"}],["$","path","19qd67",{"d":"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"}],"$undefined"]}]]}]
|
||
3c:["$","$L44",null,{"className":"shiki shiki-themes github-light github-dark","style":{"--shiki-light":"#24292e","--shiki-dark":"#e1e4e8","--shiki-light-bg":"#fff","--shiki-dark-bg":"#24292e"},"tabIndex":"0","icon":"<svg viewBox=\"0 0 24 24\"><path d=\"M 6,1 C 4.354992,1 3,2.354992 3,4 v 16 c 0,1.645008 1.354992,3 3,3 h 12 c 1.645008,0 3,-1.354992 3,-3 V 8 7 A 1.0001,1.0001 0 0 0 20.707031,6.2929687 l -5,-5 A 1.0001,1.0001 0 0 0 15,1 h -1 z m 0,2 h 7 v 3 c 0,1.645008 1.354992,3 3,3 h 3 v 11 c 0,0.564129 -0.435871,1 -1,1 H 6 C 5.4358712,21 5,20.564129 5,20 V 4 C 5,3.4358712 5.4358712,3 6,3 Z M 15,3.4140625 18.585937,7 H 16 C 15.435871,7 15,6.5641288 15,6 Z\" fill=\"currentColor\" /></svg>","children":["$","$L45",null,{"children":["$","code",null,{"children":[["$","span",null,{"className":"line","children":["$","span",null,{}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" ┌──────────────────────────────┐"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" │ Request Router │"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" │ (model ID → variant key) │"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" └────────────┬─────────────────┘"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" │"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" ┌────────────▼─────────────────┐"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" │ Delta Cache (Redis) │"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" │ sign_bits + alpha per layer │"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" │ ~9 GB per 72B variant │"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" └────────────┬─────────────────┘"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" │ cache hit"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" ┌────────────▼─────────────────┐"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" │ Shared Base Model (BF16) │"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" │ zen-max 72B: 144 GB on A100s │"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" │ zen-nano 0.6B: 1.2 GB │"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" └────────────┬─────────────────┘"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" │"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" ┌────────────▼─────────────────┐"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" │ Fused Reconstruction Kernel │"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" │ W_ft = W_base + α·sign(Δ) │"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" │ < 1ms overhead per layer │"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" └────────────┬─────────────────┘"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" │"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" ┌────────────▼─────────────────┐"}]}],"\n",["$","span",null,{"className":"line","children":"$L5d"}],"\n","$L5e","\n","$L5f","\n","$L60"]}]}]}]
|
||
3d:["$","p",null,{"children":"The architecture keeps one base model loaded per GPU cluster. All variants share it. The delta cache fits in Redis (NVMe-backed), loading on demand in under 50ms. In practice, our top-5 variants stay hot in Redis memory; the remaining variants load from NVMe on first request."}]
|
||
3e:["$","h2",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"gpu-memory-reduction","children":[["$","a",null,{"data-card":"","href":"#gpu-memory-reduction","className":"peer","children":"GPU Memory Reduction"}],["$","svg",null,{"ref":"$undefined","xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100","aria-hidden":true,"children":[["$","path","1cjeqo",{"d":"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"}],["$","path","19qd67",{"d":"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"}],"$undefined"]}]]}]
|
||
3f:["$","div",null,{"className":"relative overflow-auto prose-no-margin my-6","children":["$","table",null,{"children":[["$","thead",null,{"children":["$","tr",null,{"children":[["$","th",null,{"children":"Scenario"}],["$","th",null,{"children":"Without BitDelta"}],["$","th",null,{"children":"With BitDelta"}],["$","th",null,{"children":"Savings"}]]}]}],["$","tbody",null,{"children":[["$","tr",null,{"children":[["$","td",null,{"children":"3× zen-nano variants"}],["$","td",null,{"children":"3.6 GB"}],["$","td",null,{"children":"1.4 GB"}],["$","td",null,{"children":"61%"}]]}],["$","tr",null,{"children":[["$","td",null,{"children":"5× zen4-max variants"}],["$","td",null,{"children":"300 GB"}],["$","td",null,{"children":"192 GB"}],["$","td",null,{"children":"36%"}]]}],["$","tr",null,{"children":[["$","td",null,{"children":"2× zen-max variants"}],["$","td",null,{"children":"288 GB"}],["$","td",null,{"children":"162 GB"}],["$","td",null,{"children":"44%"}]]}],["$","tr",null,{"children":[["$","td",null,{"children":"Full 14-model catalog"}],["$","td",null,{"children":"~2.8 TB"}],["$","td",null,{"children":"~2.2 TB"}],["$","td",null,{"children":"21%"}]]}]]}]]}]}]
|
||
40:["$","p",null,{"children":"The savings are most dramatic at the smaller scales where we have many more behavioral variants. For the ultra-scale models (zen4-ultra 1T+), a single checkpoint dominates, and BitDelta’s contribution is smaller — but MonoSoup and K-Merge become more relevant for edge quantization."}]
|
||
41:["$","p",null,{"children":"The combination of BitDelta for cloud serving, MonoSoup for quality recovery, and K-Merge for edge devices gives us a coherent three-tier compression story across the full Zen catalog."}]
|
||
42:["$","hr",null,{}]
|
||
43:["$","p",null,{"children":["$","em",null,{"children":"Zen LM is a joint initiative of Hanzo AI Inc. (Techstars ‘17) and Zoo Labs Foundation (501c3)."}]}]
|
||
47:["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" (delta "}]
|
||
48:["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":">"}]
|
||
49:["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":" 0"}]
|
||
4a:["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":").to(torch.uint8) "}]
|
||
4b:["$","span",null,{"style":{"--shiki-light":"#6A737D","--shiki-dark":"#6A737D"},"children":"# 1 = positive, 0 = negative"}]
|
||
4c:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" return"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" sign_bits, alpha"}]]}]
|
||
4d:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}]
|
||
4e:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" def"}],["$","span",null,{"style":{"--shiki-light":"#6F42C1","--shiki-dark":"#B392F0"},"children":" reconstruct_weight"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":"(W_base: torch.Tensor, sign_bits: torch.Tensor, alpha: torch.Tensor) -> torch.Tensor:"}]]}]
|
||
4f:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":" \"\"\"Reconstruct fine-tuned weight from base + compressed delta.\"\"\""}]}]
|
||
50:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" signs "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" sign_bits.float() "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"*"}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":" 2"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" -"}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":" 1"}],["$","span",null,{"style":{"--shiki-light":"#6A737D","--shiki-dark":"#6A737D"},"children":" # map {0,1} → {-1,+1}"}]]}]
|
||
51:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" return"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" W_base "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"+"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" alpha "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"*"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" signs"}]]}]
|
||
52:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}]
|
||
53:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" def"}],["$","span",null,{"style":{"--shiki-light":"#6F42C1","--shiki-dark":"#B392F0"},"children":" memory_savings"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":"(d_out: "}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":"int"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":", d_in: "}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":"int"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":") -> "}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":"dict"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":":"}]]}]
|
||
54:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":" \"\"\"Compare memory usage: full delta vs BitDelta.\"\"\""}]}]
|
||
55:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" full_bytes "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" d_out "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"*"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" d_in "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"*"}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":" 2"}],["$","span",null,{"style":{"--shiki-light":"#6A737D","--shiki-dark":"#6A737D"},"children":" # bfloat16"}]]}]
|
||
56:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" bitdelta_bytes "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" d_out "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"*"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" d_in "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"//"}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":" 8"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" +"}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":" 4"}],["$","span",null,{"style":{"--shiki-light":"#6A737D","--shiki-dark":"#6A737D"},"children":" # 1-bit + float32 scale"}]]}]
|
||
57:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" return"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" {"}]]}]
|
||
58:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":" 'full_delta_mb'"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":": full_bytes "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"/"}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":" 1e6"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":","}]]}]
|
||
59:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":" 'bitdelta_mb'"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":": bitdelta_bytes "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"/"}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":" 1e6"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":","}]]}]
|
||
5a:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":" 'compression_ratio'"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":": full_bytes "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"/"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" bitdelta_bytes,"}]]}]
|
||
5b:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" }"}]}]
|
||
5c:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}]
|
||
5d:["$","span",null,{"children":" │ Inference Engine │"}]
|
||
5e:["$","span",null,{"className":"line","children":["$","span",null,{"children":" │ (vLLM with continuous batch) │"}]}]
|
||
5f:["$","span",null,{"className":"line","children":["$","span",null,{"children":" └──────────────────────────────┘"}]}]
|
||
60:["$","span",null,{"className":"line","children":["$","span",null,{"children":" "}]}]
|
||
b:[["$","meta","0",{"charSet":"utf-8"}],["$","meta","1",{"name":"viewport","content":"width=device-width, initial-scale=1"}],["$","meta","2",{"name":"theme-color","media":"(prefers-color-scheme: dark)","content":"#0A0A0A"}],["$","meta","3",{"name":"theme-color","media":"(prefers-color-scheme: light)","content":"#fff"}]]
|
||
9:null
|
||
d:[["$","title","0",{"children":"BitDelta: 1-Bit Behavioral Compression Across the Zen Model Family — Zen LM Blog | Zen LM"}],["$","meta","1",{"name":"description","content":"How BitDelta (arXiv:2402.10193) compresses fine-tuned behavioral deltas to 1-bit precision, enabling the full Zen model family — nano through ultra — to share a single GPU cluster."}],["$","meta","2",{"property":"og:title","content":"Zen LM - Open Foundation Models"}],["$","meta","3",{"property":"og:description","content":"Zen AI model family by Hanzo AI. 14 frontier models from 4B to 1T+ parameters for code, reasoning, vision, and multimodal tasks."}],["$","meta","4",{"property":"og:url","content":"https://zenlm.org"}],["$","meta","5",{"property":"og:site_name","content":"Zen LM"}],["$","meta","6",{"property":"og:type","content":"website"}],["$","meta","7",{"name":"twitter:card","content":"summary_large_image"}],["$","meta","8",{"name":"twitter:site","content":"@zenlmorg"}],["$","meta","9",{"name":"twitter:creator","content":"@zenlmorg"}],["$","meta","10",{"name":"twitter:title","content":"Zen LM - Open Foundation Models"}],["$","meta","11",{"name":"twitter:description","content":"Zen AI model family by Hanzo AI. 14 frontier models from 4B to 1T+ parameters for code, reasoning, vision, and multimodal tasks."}]]
|