Skip to content

Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.

C++

Load of DeepSeek: the app adds no Flash-Next options (request slots, RAM budget, output clamp, resource profile, memory retry) to the DeepSeek engine and waits as long as its config says

Niko1221f30d191d54f5
diff --git a/apps/host/server/native-control.mjs b/apps/host/server/native-control.mjs
index 6023686c3..92b8d554e 100644
--- a/apps/host/server/native-control.mjs
+++ b/apps/host/server/native-control.mjs
@@ -214,6 +214,8 @@ export function createNativeControl({directory,requests=()=>[],changed=()=>{},sp
if(still.length)throw new Error(`Some files could not be removed: ${still.slice(0,3).map(p=>basename(p)).join('; ')}`);
return {summary:result.summary??'Deleted',removed:result.plan?.gb??null};}
/* The configuration a load starts the engine with (before its port and key): the saved model config, the user's choices and the resource profile. The tuner measures exactly this, so a saved tuning belongs to the same choices a load makes. */
+ /* DeepSeek-V4.1-Flash runs on its own engine (strata-dsv41) that takes none of the Flash-Next options the app adds on its own (request slots, the RAM budget, the output clamp, the resource profile): a flag it does not know ends the start with "unknown option". */
+ const ownEngine=config=>config?.arch==='deepseek41'||/strata-dsv41/i.test(String(config?.exe??''));
function buildConfig(args,config){
const vision=runtimeVision(config,args.vision);
const visionPreferences=args.vision!==undefined?{ui_vision_enabled:args.vision!=='no',ui_vision_device:args.vision==='no'?config.ui_vision_device??'yes':args.vision}:{};
@@ -222,7 +224,7 @@ return {summary:result.summary??'Deleted',removed:result.plan?.gb??null};}
const values0=args.values??{},cleared='vram_reserve_mib' in values0&&(values0.vram_reserve_mib===null||values0.vram_reserve_mib===''),base0=cleared?{...config,vram_reserve_mib:undefined,[USER_KEY]:setUserFlag(config[USER_KEY],'--vram-reserve-mib',null)}:config;
let mine=captureUserArgs(base0);const asked=cleared?null:reserveChoice({...base0,[USER_KEY]:mine},snapshot.hardware,values0).asked;
if(asked!==null)mine=setUserFlag(mine,'--vram-reserve-mib',asked);
- const resources=args.resourceProfile?resourceSettings({...base0,[USER_KEY]:mine,vision},snapshot.hardware,args.resourceProfile,modelArena(args.model),values0):null;
+ const resources=args.resourceProfile&&!ownEngine(config)?resourceSettings({...base0,[USER_KEY]:mine,vision},snapshot.hardware,args.resourceProfile,modelArena(args.model),values0):null;
const cfg={...config,...visionPreferences,...(resources?{...resources,ui_resource_profile:args.resourceProfile}:{}),host:'127.0.0.1',open_browser:false,...validateNativeSettings(args.values??{}),vision};
/* The app's suggested cards only fill a gap: a model whose settings file already names its GPUs ("gpu": [1, 0], with "gpu_order": "as_given") keeps them (#3256). A card the person picked in the screen always wins. */
const namedInFile=(Array.isArray(config.gpu)?config.gpu.length>0:config.gpu!==undefined&&config.gpu!==null&&config.gpu!=='')||!!config.gpu_roles;
@@ -237,10 +239,10 @@ return {summary:result.summary??'Deleted',removed:result.plan?.gb??null};}
if(!cfg.vision&&Array.isArray(cfg.args))cfg.args=cfg.args.filter(a=>a!=='--vision');
for(const arg of cfg.args??[])if(arg.endsWith('.gguf')&&!existsSync(resolve(repo(),arg)))throw new Error('An engine argument names a missing GGUF. Restore the saved arguments or repair the files.');
/* The app's own choice of request slots (4, fewer where the card has no room) is part of the configuration, so a tune measures the engine a load will start: slots take VRAM from the expert cache. */
- const parallelChoice=packaged?chooseParallel({config:cfg,values:args.values??{},hardware:snapshot.hardware?.gpus?.length?snapshot.hardware:{gpus:hardwareProbe()??[]}}):null;
+ const parallelChoice=packaged&&!ownEngine(config)?chooseParallel({config:cfg,values:args.values??{},hardware:snapshot.hardware?.gpus?.length?snapshot.hardware:{gpus:hardwareProbe()??[]}}):null;
let parallelNote=null;
/* The agent asks for long answers (a thinking model can use most of the window): let the engine clamp the output to what is left of the context instead of refusing the request. */
- if(packaged&&cfg.fit_max_tokens===undefined)cfg.fit_max_tokens=true;
+ if(packaged&&!ownEngine(config)&&cfg.fit_max_tokens===undefined)cfg.fit_max_tokens=true;
if(parallelChoice){const applied=applyParallel(cfg,parallelChoice);for(const k of Object.keys(cfg))if(!(k in applied.cfg))delete cfg[k];Object.assign(cfg,applied.cfg);parallelNote=applied.note;}
return {cfg,resources,visionPreferences,parallelChoice,parallelNote};
}
@@ -293,7 +295,7 @@ return {summary:result.summary??'Deleted',removed:result.plan?.gb??null};}
/* The engine starts under Control's owner runtime, not as our child: a saved profile per slot, then `runtime start`. */
const used=new Set([...instances.values()].map(i=>i.profile));let slot=1;while(used.has('app-'+slot))slot++;instance.profile='app-'+slot;
instances.set(id,instance);if(!defaultId||!args.multiple||wasDefault)defaultId=id;emit();
- const startWith=value=>{writeFileSync(configPath,JSON.stringify(value,null,2),{mode:0o600});return control.stop(instance.profile).catch(()=>{}).then(()=>control.saveProfile(instance.profile,configPath)).then(()=>control.start(instance.profile,{waitSeconds:300}));};
+ const startWith=value=>{writeFileSync(configPath,JSON.stringify(value,null,2),{mode:0o600});return control.stop(instance.profile).catch(()=>{}).then(()=>control.saveProfile(instance.profile,configPath)).then(()=>control.start(instance.profile,{waitSeconds:ownEngine(config)?Math.max(300,Number(config.engine_ready_s)||300):300}));};
started=startWith(cfg);
started.then(()=>append(id,'Strata Control reports the engine is ready.'),error=>{append(id,error.message);});
try{await started;}catch(firstError){let error=firstError;
@@ -306,7 +308,7 @@ return {summary:result.summary??'Deleted',removed:result.plan?.gb??null};}
/* ONE automatic second try in all, never saved, never repeated (args.retrySafer false turns it off): with a safer memory setting when the
failure looks like a memory stop, and without several-requests-at-once when that was the app's own default (not a number the user chose).
Both changes ride on the same single try, with the plain sentence of the memory change when there is one. */
- const allowed=args.retrySafer!==false&&job.state==='running';
+ const allowed=args.retrySafer!==false&&job.state==='running'&&!ownEngine(config);
const safer=allowed?saferStart(cfg,snapshot.hardware,modelArena(args.model),said):null;
const dropParallel=allowed&&cfg.parallel>1&&!parallelChoice?.explicit;
if(!safer&&!dropParallel){instance.status='error';instance.error=said;emit();throw new Error(said);}
diff --git a/apps/host/tests/packaged-control.test.mjs b/apps/host/tests/packaged-control.test.mjs
index 957c77fcb..f21eaab1e 100644
--- a/apps/host/tests/packaged-control.test.mjs
+++ b/apps/host/tests/packaged-control.test.mjs
@@ -205,12 +205,16 @@ test('packaged: a model id with dots (DeepSeek) is listed, loaded from its run c
const id = 'deepseek-v4.1-flash-ist-das-2.00bpw';
const f = packagedFixture({ ids: [id] });
try {
+ writeFileSync(join(f.install, `strata-${id}.json`), JSON.stringify({ exe: join(f.install, 'engine-dsv41', 'strata-dsv41'), arch: 'deepseek41', tokenizer: join(f.install, 'tok'), args: ['--pack', join(f.install, 'pack'), '--max-context', '8192', '--eos', '1'], model_name: 'deepseek-v4.1-flash', port: 8080, engine_ready_s: 3600 }));
const state = await f.native.refresh(true);
assert.deepEqual(state.installed.models.map(m => m.model), [id], 'listed (the install finished but the app used to show nothing)');
assert.equal(state.installed.models[0].ready, true);
const job = await finish(f.native, f.native.operation('load', { model: id }).id);
assert.equal(job.state, 'done', job.error); // used to end with "The model configuration is outside the Strata installation."
assert.deepEqual(f.calls.filter(c => ['saveProfile', 'start'].includes(c[0])).map(c => c.slice(0, 2)), [['saveProfile', 'app-1'], ['start', 'app-1']]);
+ const flags = f.saved[0].args.filter(a => a.startsWith('--'));
+ assert.deepEqual(flags, ['--pack', '--max-context', '--eos'], 'The own engine of DeepSeek gets none of the Flash-Next options (it ended with "unknown option --batch")');
+ assert.equal(f.calls.find(c => c[0] === 'start')[2], 3600, 'it waits as long as the config says the engine needs');
const instance = f.native.state().instances[0];
assert.equal(instance.model, id);
assert.equal(instance.status, 'ready');