@qvac/llm-llamacpp 0.67.0 → 0.68.0

package/README.md

@@ -114,7 +114,7 @@ const args = {
 
 The `args` obj contains the following properties:
 
-* `files.model`: Required. An array of absolute paths to the GGUF model file(s) to load. The caller is responsible for passing the complete set of files for the model, including every shard and the `.tensors.txt` companion for multi-shard models (see [Sharded models](#sharded-models) below).
+* `files.model`: Exactly one absolute disk path: the single GGUF file or only the first shard. Fabric reads the remaining shards from the same directory.
 * `files.projectionModel`: Optional. Absolute path to the projection model file. This is required for multimodal support.
 * `config`: The model configuration object (see next section).
 * `logger`: This property is used to create a [`QvacLogger`](../logging) instance, which handles all logging functionality.
@@ -122,46 +122,24 @@ The `args` obj contains the following properties:
 
 #### Sharded models
 
-The addon no longer expands sharded models internally. If you are loading a multi-shard GGUF model, **the caller MUST pass every file** — including the `.tensors.txt` companion file that lives alongside the shards — in `files.model`. Anything missing will cause the addon to fail during weight streaming.
+Models load from disk only. Pass exactly one absolute path in `files.model`:
+the single GGUF file, or the first shard (`*-00001-of-000NN.gguf`). All shards
+must already be in the same directory with their original names. Fabric reads
+the GGUF metadata, discovers the remaining shards and reads their weights.
+No JavaScript weight buffers or `.tensors.txt` file are needed.
 
-**Required ordering for multi-shard models:**
-1. The `.tensors.txt` companion file **first**.
-2. Each `*-NNNNN-of-MMMMM.gguf` shard in **numerical order** (shard `00001` before `00002`, and so on).
-
-Example — loading a 5-shard model:
+Passing multiple paths or weight buffers is rejected. Migrate an old all-files
+list to `[firstShardPath]`. The `loadWeights()` API has been removed.
+This removes model-weight streaming, while generated output still streams as before.
 
 ```js
-const path = require('bare-path')
-const LlmLlamacpp = require('@qvac/llm-llamacpp')
-
-const dir = path.resolve('./models')
-const modelBase = 'my-big-model-Q4_K_M'
-
 const model = new LlmLlamacpp({
-  files: {
-    model: [
-      path.join(dir, `${modelBase}.tensors.txt`),
-      path.join(dir, `${modelBase}-00001-of-00005.gguf`),
-      path.join(dir, `${modelBase}-00002-of-00005.gguf`),
-      path.join(dir, `${modelBase}-00003-of-00005.gguf`),
-      path.join(dir, `${modelBase}-00004-of-00005.gguf`),
-      path.join(dir, `${modelBase}-00005-of-00005.gguf`)
-    ]
-  },
-  config,
-  logger: console,
-  opts: { stats: true }
+  files: { model: ['/absolute/models/model-00001-of-00003.gguf'] },
+  config
 })
-
 await model.load()
 ```
 
-For single-file GGUF models, pass a one-element array:
-
-```js
-files: { model: [path.join(dir, 'Llama-3.2-1B-Instruct-Q4_0.gguf')] }
-```
-
 ### 3. Create the `config` obj
 
 The `config` obj consists of a set of hyper-parameters which can be used to tweak the behaviour of the model.  

package/addon.d.ts

@@ -55,11 +55,6 @@ export type AddonBatchRunResult = {
     id?: never;
     ids: string[];
 };
-export interface LoadWeightsData {
-    filename: string;
-    chunk: Uint8Array | null;
-    completed: boolean;
-}
 export interface AddonConfigurationParams {
     path: string;
     projectionPath: string;
@@ -74,7 +69,6 @@ export interface AddonCalcTokensParams {
 }
 export interface LlamaBinding {
     createInstance(owner: LlamaInterface, configurationParams: AddonConfigurationParams, outputCallback: AddonOutputCallback, reserved: null): object;
-    loadWeights(handle: unknown, data: LoadWeightsData): Promise<void> | void;
     activate(handle: unknown): Promise<void> | void;
     activeJobs(handle: unknown): number;
     activeSlots(handle: unknown): number;
@@ -105,7 +99,6 @@ export declare class LlamaInterface {
     private readonly _binding;
     private _handle;
     constructor(binding: unknown, configurationParams: AddonConfigurationParams, outputCb: AddonOutputCallback);
-    loadWeights(weightsData: LoadWeightsData): Promise<void>;
     /**
      * Moves addon to the LISTENING state after all the initialization is done
      */

package/addon.js

@@ -80,9 +80,6 @@ class LlamaInterface {
         }
         this._handle = this._binding.createInstance(this, configurationParams, outputCb, null);
     }
-    loadWeights(weightsData) {
-        return Promise.resolve(this._binding.loadWeights(this._handle, weightsData));
-    }
     /**
      * Moves addon to the LISTENING state after all the initialization is done
      */

package/index.d.ts

@@ -16,11 +16,10 @@ type LlmLlamacppArgs = LlmLlamacpp.LlmLlamacppArgs;
 type Message = LlmLlamacpp.Message;
 type RunOptions = LlmLlamacpp.RunOptions;
 /**
- * Returns the first shard (matching `-NNNNN-of-MMMMM.gguf`) or the sole
- * entry for single-file models. Matches the C++ shard-expansion contract
- * in `GGUFShards::expandGGUFIntoShards`.
+ * Validates the single disk path. For a sharded GGUF, pass only the first
+ * shard; Fabric discovers the remaining shards. Weight streaming is unsupported.
  */
-declare function pickPrimaryGgufPath(files: string[]): string;
+declare function validateModelPath(files: string[]): string;
 interface LlmLlamacpp {
     /** The native addon, or `null` before `load()` and after `unload()`. Advanced/test access only. */
     addon: LlmLlamacpp.Addon | null;
@@ -93,8 +92,8 @@ interface LlmLlamacpp {
 interface LlmLlamacppConstructor {
     new (args: LlmLlamacppArgs): LlmLlamacpp;
     readonly prototype: LlmLlamacpp;
-    /** Returns the first shard (matching `-NNNNN-of-MMMMM.gguf`) or the sole entry for single-file models. */
-    readonly pickPrimaryGgufPath: typeof pickPrimaryGgufPath;
+    /** Validates and returns the single absolute disk path; split models require the first shard. */
+    readonly validateModelPath: typeof validateModelPath;
     readonly assessFit: typeof assessFitImpl;
 }
 /** LLM client wrapping the native LlamaInterface for inference, finetuning, and pause/resume. */
@@ -119,11 +118,6 @@ declare namespace LlmLlamacpp {
      */
     type AddonBatchRunResult = AddonModule.AddonBatchRunResult;
     interface Addon {
-        loadWeights(data: {
-            filename: string;
-            chunk: Uint8Array | null;
-            completed: boolean;
-        }, logger?: QvacLogger): Promise<void>;
         activate(): Promise<void>;
         /** Single-request admission: resolves the accepted flag plus the native-assigned job id. */
         runJob(data: AddonRunJobMessage[]): Promise<AddonRunJobResult>;
@@ -433,8 +427,9 @@ declare namespace LlmLlamacpp {
         [key: string]: string | number | boolean | string[] | undefined;
     }
     interface LlmLlamacppArgs {
+        /** One absolute disk path, or only the first shard path. Weight buffers, multiple paths and tensor-name files are unsupported. */
         files: {
-            model: string[];
+            model: [string];
             projectionModel?: string;
         };
         config: LlamaConfig;

package/index.js

@@ -273,13 +273,24 @@ function normalizeFinetuneParams(opts) {
     return out;
 }
 /**
- * Returns the first shard (matching `-NNNNN-of-MMMMM.gguf`) or the sole
- * entry for single-file models. Matches the C++ shard-expansion contract
- * in `GGUFShards::expandGGUFIntoShards`.
+ * Validates the single disk path. For a sharded GGUF, pass only the first
+ * shard; Fabric discovers the remaining shards. Weight streaming is unsupported.
  */
-function pickPrimaryGgufPath(files) {
-    const SHARD_REGEX = /-\d+-of-\d+\.gguf$/;
-    return files.find((p) => SHARD_REGEX.test(p)) || files[0];
+function validateModelPath(files) {
+    if (!Array.isArray(files) || files.length === 0) {
+        throw new TypeError("files.model must contain one absolute disk path");
+    }
+    if (files.length !== 1) {
+        throw new TypeError("Weight streaming is no longer supported. Pass only one disk path in files.model; " +
+            "for a sharded model, pass only the first shard path. Do not pass a tensor-name file.");
+    }
+    if (typeof files[0] !== "string" || files[0].length === 0 || !path.isAbsolute(files[0])) {
+        throw new TypeError("files.model[0] must be an absolute disk path string; weight buffers are not supported");
+    }
+    if (files[0].endsWith(".tensors.txt")) {
+        throw new TypeError("Weight streaming is no longer supported. Pass the first GGUF shard path, not a tensor-name file.");
+    }
+    return files[0];
 }
 // Replace media Uint8Array contents with a small summary so the logger never
 // asks V8 to JSON.stringify multi-MB binary blobs.
@@ -305,7 +316,7 @@ function sanitizePromptForLog(prompt) {
 }
 /** LLM client wrapping the native LlamaInterface for inference, finetuning, and pause/resume. */
 const LlmLlamacpp = class LlmLlamacpp {
-    static pickPrimaryGgufPath = pickPrimaryGgufPath;
+    static validateModelPath = validateModelPath;
     static assessFit = fit_1.assessFit;
     // Attached for tests; untyped because `typeof QvacResponse` is not nameable by consumers.
     static QvacResponse = infer_base_1.QvacResponse;
@@ -313,7 +324,7 @@ const LlmLlamacpp = class LlmLlamacpp {
     opts;
     logger;
     state;
-    _files;
+    _modelPath;
     _projectionModelPath;
     _config;
     _finetuneJob;
@@ -324,17 +335,7 @@ const LlmLlamacpp = class LlmLlamacpp {
     _batchHandler;
     _checkpointSaveDir;
     constructor({ files, config, logger = null, opts = {} }) {
-        if (!files || !Array.isArray(files.model) || files.model.length === 0) {
-            throw new TypeError("files.model must be a non-empty array of absolute paths");
-        }
-        for (const [i, entry] of files.model.entries()) {
-            if (typeof entry !== "string" || entry.length === 0) {
-                throw new TypeError(`files.model[${i}] must be an absolute path string`);
-            }
-            if (!path.isAbsolute(entry)) {
-                throw new TypeError(`files.model[${i}] must be an absolute path (got: ${entry})`);
-            }
-        }
+        this._modelPath = validateModelPath(files?.model);
         if (files.projectionModel !== undefined) {
             if (typeof files.projectionModel !== "string" || files.projectionModel.length === 0) {
                 throw new TypeError("files.projectionModel must be an absolute path string");
@@ -343,7 +344,6 @@ const LlmLlamacpp = class LlmLlamacpp {
                 throw new TypeError(`files.projectionModel must be an absolute path (got: ${files.projectionModel})`);
             }
         }
-        this._files = files.model;
         this._projectionModelPath = files.projectionModel || "";
         this._config = config;
         this.logger = new QvacLogger(logger);
@@ -404,18 +404,14 @@ const LlmLlamacpp = class LlmLlamacpp {
     }
     async _load() {
         this.logger.info("Starting model load");
-        const primaryGgufPath = pickPrimaryGgufPath(this._files);
         const configurationParams = {
-            path: primaryGgufPath,
+            path: this._modelPath,
             projectionPath: this._projectionModelPath,
             config: { ...this._config },
         };
         this.logger.info("Creating addon with configuration:", configurationParams);
         try {
             this.addon = this._createAddon(configurationParams);
-            if (this._files.length > 1) {
-                await this._streamShards();
-            }
             this.logger.info("Activating addon");
             await this.addon.activate();
         }
@@ -432,17 +428,6 @@ const LlmLlamacpp = class LlmLlamacpp {
         }
         this.logger.info("Model load completed successfully");
     }
-    async _streamShards() {
-        for (const filePath of this._files) {
-            const filename = path.basename(filePath);
-            const stream = fs.createReadStream(filePath);
-            for await (const chunk of stream) {
-                await this.addon.loadWeights({ filename, chunk, completed: false });
-            }
-            await this.addon.loadWeights({ filename, chunk: null, completed: true });
-            this.logger.info(`Streamed weights for ${filename}`);
-        }
-    }
     run(prompt, runOptions) {
         if (BatchHandler.isBatchInput(prompt)) {
             if (runOptions !== undefined) {
@@ -931,7 +916,7 @@ const LlmLlamacpp = class LlmLlamacpp {
 };
 // Runtime-redundant: ESM named imports need the top-level `module.exports.X =` form.
 /* eslint-disable @typescript-eslint/no-unsafe-member-access -- `module.exports` is untyped CommonJS surface. */
-module.exports.pickPrimaryGgufPath = pickPrimaryGgufPath;
+module.exports.validateModelPath = validateModelPath;
 module.exports.assessFit = fit_1.assessFit;
 module.exports.QvacResponse = infer_base_1.QvacResponse;
 module.exports = LlmLlamacpp;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@qvac/llm-llamacpp",
-  "version": "0.67.0",
+  "version": "0.68.0",
   "description": "llama addon for qvac",
   "addon": true,
   "scripts": {
@@ -79,8 +79,8 @@
   "bugs": "https://github.com/tetherto/qvac/issues",
   "homepage": "https://qvac.tether.io",
   "devDependencies": {
-    "@qvac/fabric-android-arm64": "^0.25.0",
-    "@qvac/fabric-ios": "^0.25.0",
+    "@qvac/fabric-android-arm64": "^0.26.0",
+    "@qvac/fabric-ios": "^0.26.0",
     "@types/node": "^24.2.1",
     "bare-crypto": "^1.15.3",
     "bare-process": "^4.2.2",
@@ -102,22 +102,22 @@
     "typescript-eslint": "^8.63.0"
   },
   "dependencies": {
-    "@qvac/fabric": "^0.25.0",
+    "@qvac/fabric": "^0.26.0",
     "@qvac/infer-base": "^0.8.0",
     "@qvac/logging": "^0.1.0",
     "bare-fs": "^4.5.1",
     "bare-path": "^3.0.0"
   },
   "optionalDependencies": {
-    "@qvac/fabric-linux-x64": "^0.25.0",
-    "@qvac/fabric-linux-arm64": "^0.25.0",
-    "@qvac/fabric-darwin-arm64": "^0.25.0",
-    "@qvac/fabric-darwin-x64": "^0.25.0",
-    "@qvac/fabric-win32-x64": "^0.25.0"
+    "@qvac/fabric-linux-x64": "^0.26.0",
+    "@qvac/fabric-linux-arm64": "^0.26.0",
+    "@qvac/fabric-darwin-arm64": "^0.26.0",
+    "@qvac/fabric-darwin-x64": "^0.26.0",
+    "@qvac/fabric-win32-x64": "^0.26.0"
   },
   "peerDependencies": {
-    "@qvac/fabric-android-arm64": "^0.25.0",
-    "@qvac/fabric-ios": "^0.25.0"
+    "@qvac/fabric-android-arm64": "^0.26.0",
+    "@qvac/fabric-ios": "^0.26.0"
   },
   "peerDependenciesMeta": {
     "@qvac/fabric-android-arm64": {

package/prebuilds/darwin-arm64/qvac__llm-llamacpp.bare.exports

@@ -7,7 +7,7 @@
     ],
     "current_versions": [
       {
-        "version": "0.67"
+        "version": "0.68"
       }
     ],
     "exported_symbols": [
@@ -42,7 +42,6 @@
             "__ZZN30qvac_lib_inference_addon_llama6runFitENS_10FitRequestEE8fitMutex",
             "__ZGVZN30qvac_lib_inference_addon_llama6runFitENS_10FitRequestEE8fitMutex",
             "__ZNSt3__19__any_imp17__unique_typeinfoIN24llama_finetuning_helpers21FinetuneProgressStatsEE4__idE",
-            "__ZZN10InitLoader17getLoadingContextERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEE12numInstances",
             "__ZN28qvac_lib_inference_addon_cpp6logger8JsLogger6state_E",
             "__ZNSt3__19__any_imp17__unique_typeinfoIN10LlamaModel6PromptEE4__idE",
             "__ZN28qvac_lib_inference_addon_cpp6logger8JsLogger12queue_mutex_E",
@@ -237,7 +236,6 @@
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler15failGroupLockedERKNSt3__110shared_ptrINS1_10BatchGroupEEESt13exception_ptrNS1_15SaveCachePolicyE",
             "__ZN14TextLlmContext20evalMessageWithToolsERKNSt3__16vectorI15common_chat_msgNS0_9allocatorIS2_EEEERKNS1_I16common_chat_toolNS3_IS8_EEEEbb",
             "__ZN17backend_selection13chooseBackendENS_11BackendTypeEPFv14ggml_log_levelPKcPvERKNSt3__18optionalINS7_7variantIJiNS_11MainGpuTypeEEEEEEPK13ModelMetaDataPNS8_IiEEbPbRKNS7_6vectorINS7_12basic_stringIcNS7_11char_traitsIcEENS7_9allocatorIcEEEENSP_ISR_EEEE",
-            "__ZNK18AsyncWeightsLoader12isFirstShardERKNSt3__14__fs10filesystem4pathE",
             "__ZN14MtmdLlmContext22configureReasoningTagsERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEES8_RKNS0_8optionalIN30qvac_lib_inference_addon_llama5utils13ReasoningTagsEEE",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchSchedulerC1E15LlmModelContextjjmiRK13common_paramsNSt3__18functionIFNS6_10unique_ptrI14SequenceDriverNS6_14default_deleteIS9_EEEES5_jiEEE",
             "__ZNK30qvac_lib_inference_addon_llama8batching20RuntimeStatsSnapshot22prefillTokensPerSecondEv",
@@ -257,20 +255,18 @@
             "__ZN26LlamaLazyInitializeBackend16initializeLockedERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEES8_",
             "__ZThn48_N14MtmdLlmContext18onDraftLogitsReadyEiijRKNSt3__18functionIFvRKNS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEEEE",
             "__ZN10LlamaModel32setFinetuneCancelSavesCheckpointEbRKNSt3__16vectorIyNS0_9allocatorIyEEEE",
-            "__ZN13ModelMetaData5parseERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEERK10GGUFShardsbPKc",
             "__ZN30qvac_lib_inference_addon_llama11speculative18resetDraftSequenceEP13llama_contexti",
             "__ZNK10LlamaModel15cancelInferenceEv",
             "__ZN14LlamaFinetuner17clearPauseRequestEv",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler29writeStateToFileOrThrowLockedEjRKNSt3__112basic_stringIcNS2_11char_traitsIcEENS2_9allocatorIcEEEERKNS2_6vectorIiNS6_IiEEEERKNS2_5dequeINS_5cache10CheckpointENS6_ISI_EEEE",
             "__ZN14LlamaFinetuner12requestPauseEb",
-            "__ZN10LlamaModel17resolveShardPathsER10GGUFShardsRKNSt3__112basic_stringIcNS2_11char_traitsIcEENS2_9allocatorIcEEEE",
             "__ZN12CacheManager13saveForCallerERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE",
             "__ZN14TextLlmContext18commitCacheRequestEv",
+            "__ZN30qvac_lib_inference_addon_llama5utils25getThinkingForcedOpenTextERKNSt3__112basic_stringIcNS1_11char_traitsIcEENS1_9allocatorIcEEEES9_",
             "__ZN14TextLlmContext9onFailureERKNSt3__18functionIFvRKNS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEEEE",
             "__ZN14MtmdLlmContext23advanceDecodedTextTokenEi",
             "__ZN24llama_finetuning_helpers19savePauseCheckpointEP16ggml_opt_contextRNS_23TrainingCheckpointStateEbx",
             "__ZN14MtmdLlmContext14setCacheTokensEi",
-            "__ZN30qvac_lib_inference_addon_llama5utils25getThinkingForcedOpenTextERKNSt3__112basic_stringIcNS1_11char_traitsIcEENS1_9allocatorIcEEEES9_",
             "__ZN17backend_selection26getEffectiveGpuDeviceCountERKNS_16BackendInterfaceE",
             "__ZN30qvac_lib_inference_addon_llama5utils21SequenceStateSnapshotC1EOS1_",
             "__ZN24llama_finetuning_helpers25setCurrentCheckpointStateEPNS_23TrainingCheckpointStateE",
@@ -316,13 +312,12 @@
             "__ZN30qvac_lib_inference_addon_llama8batching7Request18isOptAwaitingMediaERKNSt3__18optionalIS1_EE",
             "__ZN30qvac_lib_inference_addon_llama8batching7Request13isOptFinishedERKNSt3__18optionalIS1_EE",
             "__ZN10LlamaModel8isLoadedEv",
-            "__ZN18AsyncWeightsLoaderC2ERK10GGUFShardsR10InitLoaderRKNSt3__112basic_stringIcNS5_11char_traitsIcEENS5_9allocatorIcEEEEP13ModelMetaData",
+            "__ZThn48_N14MtmdLlmContext9loadCacheERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEb",
             "__ZN14TextLlmContext14preparePrefillERKNSt3__16vectorI15common_chat_msgNS0_9allocatorIS2_EEEERKNS1_I16common_chat_toolNS3_IS8_EEEERKNS1_INS1_IhNS3_IhEEEENS3_ISE_EEEERKNS1_I12PlannedMediaNS3_ISJ_EEEEbb",
             "__ZThn48_N14MtmdLlmContext17onPrefillCompleteEim",
             "__ZN14TextLlmContext21initializeCommonStateEv",
             "__ZNK14LlamaFinetuner31getCurrentCheckpointStateSharedEv",
             "__ZThn16_N10LlamaModelD1Ev",
-            "__ZThn48_N14MtmdLlmContext9loadCacheERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEb",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler30prepareSpeculativeDraftsLockedEPNSt3__111unique_lockINS2_5mutexEEE",
             "__ZN10LlamaModelC1EONSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEES7_ONS0_13unordered_mapIS6_S6_NS0_4hashIS6_EENS0_8equal_toIS6_EENS4_INS0_4pairIKS6_S6_EEEEEE",
             "__ZN14MtmdLlmContext23prepareSpeculativeDraftEiij",
@@ -355,17 +350,16 @@
             "__ZN14TextLlmContext23prepareSpeculativeDraftEiij",
             "__ZN14TextLlmContext29adoptCheckpointsFromCacheFileERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEy",
             "__ZN22load_fit_normalization17tuneLoadConfigMapERNSt3__113unordered_mapINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEES7_NS0_4hashIS7_EENS0_8equal_toIS7_EENS5_INS0_4pairIKS7_S7_EEEEEERK13ModelMetaDataRKNS0_8optionalIiEERK23FinetuneConfigOverridesbbbbb",
-            "__ZN18AsyncWeightsLoader31lendFirstShardAndWaitForReleaseEONSt3__110unique_ptrINS0_15basic_streambufIcNS0_11char_traitsIcEEEENS0_14default_deleteIS5_EEEE",
+            "__ZN30qvac_lib_inference_addon_llama8batching7Request22isOptGenerationPendingERKNSt3__18optionalIS1_EE",
             "__ZNK14MtmdLlmContext10ctxCeilingEv",
             "__ZThn48_N14TextLlmContext18adoptResidentStateERKNSt3__16vectorIiNS0_9allocatorIiEEEE",
-            "__ZN30qvac_lib_inference_addon_llama8batching7Request22isOptGenerationPendingERKNSt3__18optionalIS1_EE",
+            "__ZThn48_N14MtmdLlmContext13onSequenceEndERKNSt3__18functionIFvRKNS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEEEE",
             "__ZNK30qvac_lib_inference_addon_llama8batching7Request16isPrefillPendingEv",
             "__ZThn32_NK10LlamaModel10cancelByIdEy",
             "__ZN30qvac_lib_inference_addon_llama8batching20RuntimeStatsSnapshot14accumulateSlotExxRKNS0_7RequestE",
             "__ZNK14MtmdLlmContext25getToolDefinitionsDroppedEv",
             "__ZN30qvac_lib_inference_addon_llama8batching19MultiRequestBatcher13releaseBudgetEj",
             "__ZN12CacheManager10invalidateEv",
-            "__ZThn48_N14MtmdLlmContext13onSequenceEndERKNSt3__18functionIFvRKNS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEEEE",
             "__ZN14MtmdLlmContextD1Ev",
             "__ZN10LlamaModel16beginFinetuneJobEy",
             "__ZN30qvac_lib_inference_addon_llama5utils21SequenceStateSnapshot11adoptBufferENSt3__16vectorIhNS2_9allocatorIhEEEEi",
@@ -388,7 +382,6 @@
             "__ZThn48_N14TextLlmContext14preparePrefillERKNSt3__16vectorI15common_chat_msgNS0_9allocatorIS2_EEEERKNS1_I16common_chat_toolNS3_IS8_EEEERKNS1_INS1_IhNS3_IhEEEENS3_ISE_EEEERKNS1_I12PlannedMediaNS3_ISJ_EEEEbb",
             "__ZN14MtmdLlmContext9loadMediaERKNSt3__16vectorIhNS0_9allocatorIhEEEE",
             "__ZN14TextLlmContext23restoreCacheStateTokensERKNSt3__16vectorIiNS0_9allocatorIiEEEE",
-            "__ZN18AsyncWeightsLoader20joinFirstShardWorkerEv",
             "__ZN30qvac_lib_inference_addon_llama8batching24generationBudgetExceededEjjij",
             "__ZNK14MtmdLlmContext28appendCheckpointsToCacheFileERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE",
             "__ZThn48_N14TextLlmContext29adoptCheckpointsFromCacheFileERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEy",
@@ -401,8 +394,8 @@
             "__ZNK12CacheManager15isCacheDisabledEv",
             "__ZNK14MtmdLlmContext14getCacheTokensEv",
             "__ZN30qvac_lib_inference_addon_llama5utils21SequenceStateSnapshot5clearEv",
-            "__ZN14TextLlmContext15adoptDonorStateERKN30qvac_lib_inference_addon_llama5cache10DonorStateERKNS1_6LedgerEb",
             "__ZN14TextLlmContext15reconcilePromptERKNSt3__16vectorIiNS0_9allocatorIiEEEEb",
+            "__ZN14TextLlmContext15adoptDonorStateERKN30qvac_lib_inference_addon_llama5cache10DonorStateERKNS1_6LedgerEb",
             "__ZThn48_NK14TextLlmContext19residentStateTokensEv",
             "__ZN17backend_selection23getSplitDeviceSelectionERKNS_16BackendInterfaceE",
             "__ZN14TextLlmContext12syncPositionEi",
@@ -508,11 +501,12 @@
             "__ZN14TextLlmContext21rollbackFailedRequestEv",
             "__ZN17backend_selection20splitModeDeviceNamesERKNS_16BackendInterfaceERKNSt3__112basic_stringIcNS3_11char_traitsIcEENS3_9allocatorIcEEEE",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler12submitLockedEONS1_13QueuedRequestE",
+            "__ZN13ModelMetaData5parseERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEPKc",
             "__ZNK30qvac_lib_inference_addon_llama8batching19MultiRequestBatcher12draftDroppedEj",
             "__ZN14MtmdLlmContext13onLogitsReadyEijRKNSt3__18functionIFvRKNS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEEEEP10LlamaBatch",
             "__ZN14TextLlmContext23resetStateKeepingMemoryEb",
             "__ZN30qvac_lib_inference_addon_llama11speculative18SpeculativeRuntime6createER13common_paramsP11llama_modelP13llama_context",
-            "__ZNK18AsyncWeightsLoader25hasIndividualStreamedFileERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE",
+            "__ZThn48_N14TextLlmContext8onCancelERKNSt3__18functionIFvRKNS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEEEE",
             "__ZN14MtmdLlmContext24snapshotPreRequestCursorEv",
             "__ZNK30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler19donorHitsForTestingEv",
             "__ZN14MtmdLlmContext18onDraftLogitsReadyEiijRKNSt3__18functionIFvRKNS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEEEE",
@@ -539,16 +533,14 @@
             "__ZN12CacheManager17atomicPromoteFileERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEES8_",
             "__ZN14MtmdLlmContext14requireSamplerEv",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler19discardConversationERKNSt3__112basic_stringIcNS2_11char_traitsIcEENS2_9allocatorIcEEEE",
-            "__ZN18AsyncWeightsLoader17setWeightsForFileERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEONS0_10unique_ptrINS0_15basic_streambufIcS3_EENS0_14default_deleteISB_EEEE",
             "__ZN14MtmdLlmContext4stopEv",
-            "__ZThn48_N14TextLlmContext8onCancelERKNSt3__18functionIFvRKNS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEEEE",
             "__ZN12CacheManager20isFileMissingOrEmptyERKNSt3__14__fs10filesystem4pathE",
             "__ZN14TextLlmContext27restorePreRequestCacheStateEv",
             "__ZN14TextLlmContext24captureHistoryCheckpointEi",
             "__ZN22load_fit_normalization22productionDependenciesEPFv14ggml_log_levelPKcPvE",
             "__ZN30qvac_lib_inference_addon_llama28applyGenerationParamHandlersEP8js_env_sRN28qvac_lib_inference_addon_cpp2js6ObjectER16GenerationParams",
             "__ZN30qvac_lib_inference_addon_llama11speculative19SpeculativeSequence12discardDraftEv",
-            "__ZNK18AsyncWeightsLoader20shouldLendFirstShardERKNSt3__14__fs10filesystem4pathE",
+            "__ZNK30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler15hasValidDriverFEv",
             "__ZN10LlamaModel19flushResidentCachesEv",
             "__ZN14TextLlmContext24rebuildSamplerFromLedgerERKN30qvac_lib_inference_addon_llama5cache6LedgerE",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler28serviceCheckpointStopsLockedEv",
@@ -557,7 +549,6 @@
             "__ZN30qvac_lib_inference_addon_llama5utils20historyReasoningTagsEPK21common_chat_templatesPK11llama_modelb",
             "__ZN24llama_finetuning_helpers20clearPauseCheckpointERKNSt3__14__fs10filesystem4pathE",
             "__ZN14MtmdLlmContext30capturePreRequestCacheSnapshotEv",
-            "__ZN18AsyncWeightsLoader30extractIndividualStreamedFilesEv",
             "__ZN30qvac_lib_inference_addon_llama8batching20computeObservedStatsENSt3__16chrono10time_pointINS2_12steady_clockENS2_8durationIxNS1_5ratioILl1ELl1000000000EEEEEEERKNS0_7RequestENS1_8optionalI20GenerationStopReasonEE",
             "__ZN10LlamaModel15getCommonParamsEv",
             "__ZN14MtmdLlmContextC2ERK13common_paramsRK15LlmModelContextP12mtmd_contextiiy",
@@ -569,7 +560,7 @@
             "__ZThn24_N10LlamaModel7processERKNSt3__13anyEy",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler5clearEv",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler29serviceNextMediaSegmentLockedEPNSt3__111unique_lockINS2_5mutexEEE",
-            "__ZNK30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler15hasValidDriverFEv",
+            "__ZThn48_NK14MtmdLlmContext9saveCacheERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE",
             "__ZN30qvac_lib_inference_addon_llama5utils13isGemma4ModelEPK11llama_model",
             "__ZN10LlamaModel24validateCheckpointBudgetERNS_15ReloadableStateE",
             "__ZN22load_fit_normalization31validateMobileMultiDeviceConfigERKNSt3__113unordered_mapINS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEES7_NS0_4hashIS7_EENS0_8equal_toIS7_EENS5_INS0_4pairIKS7_S7_EEEEEE16llama_split_mode",
@@ -580,7 +571,6 @@
             "__ZN24llama_finetuning_helpers21tryHandlePauseRequestEP16ggml_opt_contextPNS_23TrainingCheckpointStateEbxx",
             "__ZN10LlamaModel21isMultiBatchActivatedERNS_15ReloadableStateE",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchSchedulerC2E15LlmModelContextjjmiRK13common_paramsNSt3__18functionIFNS6_10unique_ptrI14SequenceDriverNS6_14default_deleteIS9_EEEES5_jiEEE",
-            "__ZThn48_NK14MtmdLlmContext9saveCacheERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE",
             "__ZN12CacheManager24isParentDirectoryMissingERKNSt3__14__fs10filesystem4pathE",
             "__ZN14MtmdLlmContext16sampleFromLogitsEijRKNSt3__18functionIFvRKNS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEEEEP10LlamaBatch",
             "__ZN14MtmdLlmContext24rebuildSamplerFromLedgerERKN30qvac_lib_inference_addon_llama5cache6LedgerE",
@@ -599,7 +589,6 @@
             "__ZN30qvac_lib_inference_addon_llama5utils21SequenceStateSnapshot19seedEmptyForTestingEi",
             "__ZThn48_N14MtmdLlmContext29adoptCheckpointsFromCacheFileERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEy",
             "__ZThn48_N14TextLlmContextD0Ev",
-            "__ZN18AsyncWeightsLoaderC1ERK10GGUFShardsR10InitLoaderRKNSt3__112basic_stringIcNS5_11char_traitsIcEENS5_9allocatorIcEEEEP13ModelMetaData",
             "__ZN17backend_selection20parseBackendOverrideERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE",
             "__ZN12CacheManager9loadCacheEv",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler14enqueueSaveJobERKNSt3__112basic_stringIcNS2_11char_traitsIcEENS2_9allocatorIcEEEEb",
@@ -614,7 +603,6 @@
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler29verifySpeculativeDraftsLockedEv",
             "__ZNK14TextLlmContext28appendCheckpointsToCacheFileERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE",
             "__ZN12CacheManagerC1EP10LlmContextNSt3__18functionIFvbEEE",
-            "__ZNK18AsyncWeightsLoader11isLastShardERKNSt3__14__fs10filesystem4pathE",
             "__ZN30qvac_lib_inference_addon_llama11speculative22applySpeculativeConfigERKNS0_17SpeculativeConfigER13common_params",
             "__ZN14TextLlmContext19appendResidentTokenEi",
             "__ZN30qvac_lib_inference_addon_llama8batching7Request23isOptAwaitingCheckpointERKNSt3__18optionalIS1_EE",
@@ -638,7 +626,6 @@
             "__ZN14LlamaFinetuner24validateFinetuningParamsERKN30qvac_lib_inference_addon_llama21LlamaFinetuningParamsE",
             "__ZN14MtmdLlmContext15checkAntipromptEmi",
             "__ZN30qvac_lib_inference_addon_llama5utils21SequenceStateSnapshotC2EOS1_",
-            "__ZN13ModelMetaData28FirstFileFromGgufStreamState7provideER13BorrowablePtrINSt3__115basic_streambufIcNS2_11char_traitsIcEEEEE",
             "__ZN10LlamaModel20isConcurrentEligibleERKNS_6PromptE",
             "__ZNK30qvac_lib_inference_addon_llama8batching7Request15isAwaitingMediaEv",
             "__ZNK30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler15numActiveLockedEv",
@@ -716,18 +703,18 @@
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler23cancelKeyDeferredLockedEv",
             "__ZNK30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler13hasWorkLockedEv",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler18notifyDoneNoexceptEj",
+            "__ZN30qvac_lib_inference_addon_llama5utils14isHarmonyModelEPK11llama_model",
             "__ZN10LlamaModel10resetStateEb",
-            "__ZN14TextLlmContext24snapshotPreRequestCursorEv",
             "__ZN10LlamaModel22processConcurrentBatchERKNSt3__16vectorINS_6PromptENS0_9allocatorIS2_EEEEy",
-            "__ZN14MtmdLlmContext9loadMediaERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE",
+            "__ZN14TextLlmContext24snapshotPreRequestCursorEv",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler17prefillCompleteFnEv",
-            "__ZN14TextLlmContext19generateSpeculativeERKNSt3__18functionIFvRKNS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEEEERj",
+            "__ZN14MtmdLlmContext9loadMediaERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE",
             "__ZN14MtmdLlmContext14preparePrefillERKNSt3__16vectorI15common_chat_msgNS0_9allocatorIS2_EEEERKNS1_I16common_chat_toolNS3_IS8_EEEERKNS1_INS1_IhNS3_IhEEEENS3_ISE_EEEERKNS1_I12PlannedMediaNS3_ISJ_EEEEbb",
             "__ZNK30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler24teardownPendingForLockedEj",
+            "__ZN14TextLlmContext19generateSpeculativeERKNSt3__18functionIFvRKNS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEEEERj",
             "__ZNK14TextLlmContext9saveCacheERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE",
             "__Z33qvacLibInferenceAddonLlamaExportsP8js_env_sP10js_value_s",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler25ensureWorkerStartedLockedEv",
-            "__ZN30qvac_lib_inference_addon_llama5utils14isHarmonyModelEPK11llama_model",
             "__ZN14MtmdLlmContext13onSequenceEndERKNSt3__18functionIFvRKNS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEEEE"
           ],
           "weak": [
@@ -764,7 +751,6 @@
             "__ZN28qvac_lib_inference_addon_cpp2js11JsAsyncTask13onEnvTeardownImEEvP22js_deferred_teardown_sPv",
             "__ZN28qvac_lib_inference_addon_cpp6logger8JsLogger13onEnvTeardownEPv",
             "__ZN28qvac_lib_inference_addon_cpp11JsInterface9setLoggerEP8js_env_sP18js_callback_info_s",
-            "__ZN28qvac_lib_inference_addon_cpp11JsInterface11loadWeightsEP8js_env_sP18js_callback_info_s",
             "__ZN28qvac_lib_inference_addon_cpp16OutputCallBackJs13onEnvTeardownEPv",
             "__ZN28qvac_lib_inference_addon_cpp16OutputCallBackJs16jsOutputCallbackEP10uv_async_s"
           ]