@qvac/llm-llamacpp 0.64.2 → 0.64.3

package/README.md

@@ -265,9 +265,9 @@ projector runs on CPU. The resolved choice is logged at verbosity ≥ 2 as
 
 `spec-type: 'draft-mtp'` turns on llama-server's multi-token-prediction speculative decoding for models that ship their MTP layers (`blk.N.nextn.*`, e.g. Qwen3.5 / Qwen3.6 GGUFs that keep them; quantizations that strip them fail to load with this option unless an external head is given, see below). Every step the MTP head drafts up to `spec-draft-n-max` tokens from the model's own hidden states, the model verifies the sampled token and the draft in one decode, and the longest matching prefix plus one new token is kept. The sampler decides every kept token, so sampling settings, grammars and stop conditions behave as without speculation. The implementation follows llama-server step by step: the same draft limits, rollback by trimming or by a checkpoint for memory that cannot trim, and the same replay.
 
-For a model without MTP layers, give an external MTP head as `spec-draft-model` (llama-server's `--spec-type draft-mtp -md <head>`): a GGUF with MTP layers for the same model, such as the MTP quantization of it, or a Gemma 4 assistant for its Gemma 4 model. The head is loaded next to the model and placed like it (`device`, `gpu-layers`), and the load's fit and `assessFit` count its weights as well as its context. A head without MTP layers fails the load, and `assessFit` refuses it with `unsupported-config`. A head for another model, with a different hidden width or vocabulary, also fails the load, and `assessFit` refuses it the same way. Fabric cannot measure a Gemma 4 assistant on its own, so the fits leave it out, as for DFlash.
+For a model without MTP layers, give an external MTP head as `spec-draft-model` (llama-server's `--spec-type draft-mtp -md <head>`): a GGUF with MTP layers for the same model, such as the MTP quantization of it, or a Gemma 4 assistant for its Gemma 4 model. The head is loaded next to the model and placed like it (`device`, `gpu-layers`), and the load's fit and `assessFit` count its weights as well as its context. A head without MTP layers fails the load, and `assessFit` refuses it with `unsupported-config`. A head for another model, with a different hidden width or vocabulary, also fails the load, and `assessFit` refuses it the same way. A Gemma 4 assistant reads the model's own tensors, so fabric measures it next to the model, as the load creates it.
 
-`spec-type: 'draft-dflash'` drafts with a separate DFlash model instead, given as `spec-draft-model` (an absolute path; llama-server's `-md`). The DFlash model reads the hidden states of the target layers it was trained on and denoises a whole block of draft tokens in one pass, so a step drafts up to its block size minus one tokens (`spec-draft-n-max` caps it further). It is loaded next to the model and placed like it (`device`, `gpu-layers`). The load's fit and `assessFit` pass it to fabric as an extra model, but fabric cannot measure a DFlash model yet: it logs `failed to measure the memory of the extra model, fitting without it`, so neither counts the draft model's memory. Leave room for it yourself. Everything else (verification, rollback, batching, caches, stats) is the same as for MTP.
+`spec-type: 'draft-dflash'` drafts with a separate DFlash model instead, given as `spec-draft-model` (an absolute path; llama-server's `-md`). The DFlash model reads the hidden states of the target layers it was trained on and denoises a whole block of draft tokens in one pass, so a step drafts up to its block size minus one tokens (`spec-draft-n-max` caps it further). It is loaded next to the model and placed like it (`device`, `gpu-layers`). The load's fit and `assessFit` count its weights and context, measured next to the model when the drafter borrows the model's embeddings and output head. A draft model fabric still cannot measure is left out of both, and fabric logs `failed to measure the memory of the extra model, fitting without it`. Everything else (verification, rollback, batching, caches, stats) is the same as for MTP.
 
 MTP and DFlash work on single prompts, multimodal prompts and continuous batching (`parallel >= 2`), together with `cacheKey` conversations: the draft context's state travels with checkpoints and the RAM tier, and a `cacheKey` file (target state only, like llama-server's slot files) restarts drafting from the next decoded token.
 
@@ -455,7 +455,7 @@ fit.hostBytes // the same, for the trailing host row
 
 `config` is the load, exactly as `loadModel` takes it. The projection resolves it with the same code that load runs, so every setting reaches the fitter the way it would reach the engine, and a load the engine would refuse is refused here as `status: "error"` with `unsupported-config`. A setting left out takes llama's default.
 
-With `spec-type: 'draft-mtp'` the MTP draft context is fitted next to the model, as the load fits it, and its memory is in the verdict and in the per-device figures; on a model or head without MTP layers the load fails, so the projection is refused with `unsupported-config`. A DFlash draft model or a Gemma 4 assistant is passed to the fit the same way, but fabric cannot measure either yet, so neither the verdict nor the figures count it (see [Speculative decoding](#speculative-decoding-mtp-dflash)).
+With `spec-type: 'draft-mtp'` the MTP draft context is fitted next to the model, as the load fits it, and its memory is in the verdict and in the per-device figures; on a model or head without MTP layers the load fails, so the projection is refused with `unsupported-config`. A DFlash draft model or a Gemma 4 assistant is fitted the same way, measured next to the model since it reads the model's tensors, and is in the verdict and the figures too (see [Speculative decoding](#speculative-decoding-mtp-dflash)).
 
 Pinning `gpu-layers` fixes the placement: the fitter refuses to move layers off a device the load claimed, so the answer is whether that exact placement fits, never a reduced one. Leave it unset for a projection that can place the model itself.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@qvac/llm-llamacpp",
-  "version": "0.64.2",
+  "version": "0.64.3",
   "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": "0.23.0",
-    "@qvac/fabric-ios": "0.23.0",
+    "@qvac/fabric-android-arm64": "^0.23.1",
+    "@qvac/fabric-ios": "^0.23.1",
     "@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": "^0.23.0",
+    "@qvac/fabric": "^0.23.1",
     "@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": "^0.23.0",
-    "@qvac/fabric-linux-arm64": "^0.23.0",
-    "@qvac/fabric-darwin-arm64": "^0.23.0",
-    "@qvac/fabric-darwin-x64": "^0.23.0",
-    "@qvac/fabric-win32-x64": "^0.23.0"
+    "@qvac/fabric-linux-x64": "^0.23.1",
+    "@qvac/fabric-linux-arm64": "^0.23.1",
+    "@qvac/fabric-darwin-arm64": "^0.23.1",
+    "@qvac/fabric-darwin-x64": "^0.23.1",
+    "@qvac/fabric-win32-x64": "^0.23.1"
   },
   "peerDependencies": {
-    "@qvac/fabric-android-arm64": "^0.23.0",
-    "@qvac/fabric-ios": "^0.23.0"
+    "@qvac/fabric-android-arm64": "^0.23.1",
+    "@qvac/fabric-ios": "^0.23.1"
   },
   "peerDependenciesMeta": {
     "@qvac/fabric-android-arm64": {

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

@@ -7,7 +7,7 @@
     ],
     "current_versions": [
       {
-        "version": "0.64.2"
+        "version": "0.64.3"
       }
     ],
     "exported_symbols": [
@@ -193,7 +193,6 @@
             "__ZN14MtmdLlmContext35refreshCurrentCacheTokensFromMemoryEv",
             "__ZN30qvac_lib_inference_addon_llama5utils17resolveToolChoiceERKNSt3__18optionalINS1_12basic_stringIcNS1_11char_traitsIcEENS1_9allocatorIcEEEEEERKNS1_6vectorI16common_chat_toolNS6_ISD_EEEE",
             "__ZN30qvac_lib_inference_addon_llama8batching7RequestC1EjONSt3__16vectorIiNS2_9allocatorIiEEEEji",
-            "__ZNK30qvac_lib_inference_addon_llama11speculative19SpeculativeFitModel9addMemoryEjRKNSt3__16vectorIP19ggml_backend_deviceNS2_9allocatorIS5_EEEERNS3_I25common_device_memory_dataNS6_ISB_EEEE",
             "__ZN30qvac_lib_inference_addon_llama8batching14timeDecodeStepEP13llama_contextR11llama_batchRKNSt3__18functionIFiS2_S4_EEERKNS6_IFvS2_EEE",
             "__ZN30qvac_lib_inference_addon_llama8batching19MultiRequestBatcher20completeMediaBarrierEjiRKNSt3__18functionIFvjimEEE",
             "__ZN14TextLlmContext17removeLastNTokensEi",
@@ -384,7 +383,6 @@
             "__ZThn48_NK14MtmdLlmContext8getNPastEv",
             "__ZN14TextLlmContext18onDraftLogitsReadyEiijRKNSt3__18functionIFvRKNS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEEEE",
             "__ZNK12CacheManager15isCacheDisabledEv",
-            "__ZN30qvac_lib_inference_addon_llama11speculative20fitLeavesOutMtpDraftERKNS0_9GgufShapeE",
             "__ZNK14MtmdLlmContext14getCacheTokensEv",
             "__ZN30qvac_lib_inference_addon_llama5utils21SequenceStateSnapshot5clearEv",
             "__ZN14TextLlmContext15reconcilePromptERKNSt3__16vectorIiNS0_9allocatorIiEEEEb",
@@ -565,6 +563,7 @@
             "__ZN14MtmdLlmContext24rebuildSamplerFromLedgerERKN30qvac_lib_inference_addon_llama5cache6LedgerE",
             "__ZNK30qvac_lib_inference_addon_llama11speculative18SpeculativeRuntime13resetSequenceEi",
             "__ZN14MtmdLlmContext15reconcilePromptE11PrefillPlanRKN30qvac_lib_inference_addon_llama5cache6LedgerEb",
+            "__ZNK30qvac_lib_inference_addon_llama11speculative19SpeculativeFitModel9addMemoryEPKcRK18llama_model_paramsRK20llama_context_paramsRKNSt3__16vectorIP19ggml_backend_deviceNSA_9allocatorISD_EEEERNSB_I25common_device_memory_dataNSE_ISJ_EEEE",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler15StepUnlockGuardD1Ev",
             "__ZN26LlamaLazyInitializeBackend10initializeERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEES8_",
             "__ZNK13ModelMetaData9tryGetU32EPKc",

package/prebuilds/darwin-x64/qvac__llm-llamacpp.bare.exports

@@ -7,7 +7,7 @@
     ],
     "current_versions": [
       {
-        "version": "0.64.2"
+        "version": "0.64.3"
       }
     ],
     "exported_symbols": [
@@ -455,9 +455,9 @@
             "__ZTSZN30qvac_lib_inference_addon_llama9assessFitEP8js_env_sP18js_callback_info_sEUlvE_",
             "__ZTSNSt3__111__match_anyIcEE",
             "__ZTSN28qvac_lib_inference_addon_cpp17MultiJobSchedulerE",
-            "__ZTSNSt3__120__shared_ptr_emplaceIN28qvac_lib_inference_addon_cpp16OutputCallBackJs5StateENS_9allocatorIS3_EEEE",
             "__ZTSZN28qvac_lib_inference_addon_cpp17makeQueueCallbackIN24llama_finetuning_helpers21FinetuneProgressStatsEEENSt3__18functionIFvRKT_EEENS3_10shared_ptrINS_11OutputQueueEEENS3_13shared_futureIyEEEUlRKS2_E_",
             "__ZTSNSt3__110__function6__funcIZN28qvac_lib_inference_addon_cpp2js11JsAsyncTask3runIZNS2_7AddonJs9cancelJobENS_8optionalIyEEEUlvE_EEP10js_value_sP8js_env_sOT_EUlSD_RKNS_9monostateEE_NS_9allocatorISJ_EEFSB_SD_SI_EEE",
+            "__ZTSNSt3__120__shared_ptr_emplaceIN28qvac_lib_inference_addon_cpp16OutputCallBackJs5StateENS_9allocatorIS3_EEEE",
             "__ZTI10LlmContext",
             "__ZTINSt3__110__function6__baseIFP10js_value_sRKNS_6vectorINS_12basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEENS8_ISA_EEEEEEE",
             "__ZTSNSt3__120__shared_ptr_emplaceIN28qvac_lib_inference_addon_cpp9out_handl20JsErrorOutputHandlerENS_9allocatorIS3_EEEE",
@@ -578,7 +578,6 @@
             "__ZN14MtmdLlmContext17removeLastNTokensEi",
             "__ZN30qvac_lib_inference_addon_llama11speculative18SpeculativeRuntimeD2Ev",
             "__ZN30qvac_lib_inference_addon_llama5utils17resolveToolChoiceERKNSt3__18optionalINS1_12basic_stringIcNS1_11char_traitsIcEENS1_9allocatorIcEEEEEERKNS1_6vectorI16common_chat_toolNS6_ISD_EEEE",
-            "__ZNK30qvac_lib_inference_addon_llama11speculative19SpeculativeFitModel9addMemoryEjRKNSt3__16vectorIP19ggml_backend_deviceNS2_9allocatorIS5_EEEERNS3_I25common_device_memory_dataNS6_ISB_EEEE",
             "__ZN14MtmdLlmContext10resetMediaEv",
             "__ZN30qvac_lib_inference_addon_llama8batching22finalizeTerminalDriverER14SequenceDriverNS0_10StopReasonEbRKNSt3__18functionIFvRKNS4_12basic_stringIcNS4_11char_traitsIcEENS4_9allocatorIcEEEEEEE",
             "__ZN30qvac_lib_inference_addon_llama5utils21SequenceStateSnapshot10adoptEmptyEi",
@@ -668,7 +667,6 @@
             "__ZN14TextLlmContextC2ER13common_paramsNSt3__110unique_ptrI18common_init_resultNS2_14default_deleteIS4_EEEENS3_IN30qvac_lib_inference_addon_llama11speculative18SpeculativeRuntimeENS5_ISA_EEEE",
             "__ZN14TextLlmContext17beginCacheRequestEv",
             "__ZNK12CacheManager15isCacheDisabledEv",
-            "__ZN30qvac_lib_inference_addon_llama11speculative20fitLeavesOutMtpDraftERKNS0_9GgufShapeE",
             "__ZThn48_NK14TextLlmContext19residentStateTokensEv",
             "__ZN14MtmdLlmContext18commitCacheRequestEv",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler23recordPendingSlotCancelEjy",
@@ -1070,6 +1068,7 @@
             "__ZN10LlamaModel21isMultiBatchActivatedERNS_15ReloadableStateE",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchSchedulerC2E15LlmModelContextjjmiRK13common_paramsNSt3__18functionIFNS6_10unique_ptrI14SequenceDriverNS6_14default_deleteIS9_EEEES5_jiEEE",
             "__ZN14MtmdLlmContext15reconcilePromptE11PrefillPlanRKN30qvac_lib_inference_addon_llama5cache6LedgerEb",
+            "__ZNK30qvac_lib_inference_addon_llama11speculative19SpeculativeFitModel9addMemoryEPKcRK18llama_model_paramsRK20llama_context_paramsRKNSt3__16vectorIP19ggml_backend_deviceNSA_9allocatorISD_EEEERNSB_I25common_device_memory_dataNSE_ISJ_EEEE",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler15StepUnlockGuardD1Ev",
             "__ZN26LlamaLazyInitializeBackend10initializeERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEES8_",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler19drainFinishedLockedEPNSt3__111unique_lockINS2_5mutexEEE",

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

@@ -7,7 +7,7 @@
     ],
     "current_versions": [
       {
-        "version": "0.64.2"
+        "version": "0.64.3"
       }
     ],
     "exported_symbols": [
@@ -193,7 +193,6 @@
             "__ZN14MtmdLlmContext35refreshCurrentCacheTokensFromMemoryEv",
             "__ZN30qvac_lib_inference_addon_llama5utils17resolveToolChoiceERKNSt3__18optionalINS1_12basic_stringIcNS1_11char_traitsIcEENS1_9allocatorIcEEEEEERKNS1_6vectorI16common_chat_toolNS6_ISD_EEEE",
             "__ZN30qvac_lib_inference_addon_llama8batching7RequestC1EjONSt3__16vectorIiNS2_9allocatorIiEEEEji",
-            "__ZNK30qvac_lib_inference_addon_llama11speculative19SpeculativeFitModel9addMemoryEjRKNSt3__16vectorIP19ggml_backend_deviceNS2_9allocatorIS5_EEEERNS3_I25common_device_memory_dataNS6_ISB_EEEE",
             "__ZN30qvac_lib_inference_addon_llama8batching14timeDecodeStepEP13llama_contextR11llama_batchRKNSt3__18functionIFiS2_S4_EEERKNS6_IFvS2_EEE",
             "__ZN30qvac_lib_inference_addon_llama8batching19MultiRequestBatcher20completeMediaBarrierEjiRKNSt3__18functionIFvjimEEE",
             "__ZN14TextLlmContext17removeLastNTokensEi",
@@ -384,7 +383,6 @@
             "__ZThn48_NK14MtmdLlmContext8getNPastEv",
             "__ZN14TextLlmContext18onDraftLogitsReadyEiijRKNSt3__18functionIFvRKNS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEEEE",
             "__ZNK12CacheManager15isCacheDisabledEv",
-            "__ZN30qvac_lib_inference_addon_llama11speculative20fitLeavesOutMtpDraftERKNS0_9GgufShapeE",
             "__ZNK14MtmdLlmContext14getCacheTokensEv",
             "__ZN30qvac_lib_inference_addon_llama5utils21SequenceStateSnapshot5clearEv",
             "__ZN14TextLlmContext15reconcilePromptERKNSt3__16vectorIiNS0_9allocatorIiEEEEb",
@@ -565,6 +563,7 @@
             "__ZN14MtmdLlmContext24rebuildSamplerFromLedgerERKN30qvac_lib_inference_addon_llama5cache6LedgerE",
             "__ZNK30qvac_lib_inference_addon_llama11speculative18SpeculativeRuntime13resetSequenceEi",
             "__ZN14MtmdLlmContext15reconcilePromptE11PrefillPlanRKN30qvac_lib_inference_addon_llama5cache6LedgerEb",
+            "__ZNK30qvac_lib_inference_addon_llama11speculative19SpeculativeFitModel9addMemoryEPKcRK18llama_model_paramsRK20llama_context_paramsRKNSt3__16vectorIP19ggml_backend_deviceNSA_9allocatorISD_EEEERNSB_I25common_device_memory_dataNSE_ISJ_EEEE",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler15StepUnlockGuardD1Ev",
             "__ZN26LlamaLazyInitializeBackend10initializeERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEES8_",
             "__ZNK13ModelMetaData9tryGetU32EPKc",

package/prebuilds/ios-arm64-simulator/qvac__llm-llamacpp.bare.exports

@@ -7,7 +7,7 @@
     ],
     "current_versions": [
       {
-        "version": "0.64.2"
+        "version": "0.64.3"
       }
     ],
     "exported_symbols": [
@@ -193,7 +193,6 @@
             "__ZN14MtmdLlmContext35refreshCurrentCacheTokensFromMemoryEv",
             "__ZN30qvac_lib_inference_addon_llama5utils17resolveToolChoiceERKNSt3__18optionalINS1_12basic_stringIcNS1_11char_traitsIcEENS1_9allocatorIcEEEEEERKNS1_6vectorI16common_chat_toolNS6_ISD_EEEE",
             "__ZN30qvac_lib_inference_addon_llama8batching7RequestC1EjONSt3__16vectorIiNS2_9allocatorIiEEEEji",
-            "__ZNK30qvac_lib_inference_addon_llama11speculative19SpeculativeFitModel9addMemoryEjRKNSt3__16vectorIP19ggml_backend_deviceNS2_9allocatorIS5_EEEERNS3_I25common_device_memory_dataNS6_ISB_EEEE",
             "__ZN30qvac_lib_inference_addon_llama8batching14timeDecodeStepEP13llama_contextR11llama_batchRKNSt3__18functionIFiS2_S4_EEERKNS6_IFvS2_EEE",
             "__ZN30qvac_lib_inference_addon_llama8batching19MultiRequestBatcher20completeMediaBarrierEjiRKNSt3__18functionIFvjimEEE",
             "__ZN14TextLlmContext17removeLastNTokensEi",
@@ -384,7 +383,6 @@
             "__ZThn48_NK14MtmdLlmContext8getNPastEv",
             "__ZN14TextLlmContext18onDraftLogitsReadyEiijRKNSt3__18functionIFvRKNS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEEEE",
             "__ZNK12CacheManager15isCacheDisabledEv",
-            "__ZN30qvac_lib_inference_addon_llama11speculative20fitLeavesOutMtpDraftERKNS0_9GgufShapeE",
             "__ZNK14MtmdLlmContext14getCacheTokensEv",
             "__ZN30qvac_lib_inference_addon_llama5utils21SequenceStateSnapshot5clearEv",
             "__ZN14TextLlmContext15reconcilePromptERKNSt3__16vectorIiNS0_9allocatorIiEEEEb",
@@ -565,6 +563,7 @@
             "__ZN14MtmdLlmContext24rebuildSamplerFromLedgerERKN30qvac_lib_inference_addon_llama5cache6LedgerE",
             "__ZNK30qvac_lib_inference_addon_llama11speculative18SpeculativeRuntime13resetSequenceEi",
             "__ZN14MtmdLlmContext15reconcilePromptE11PrefillPlanRKN30qvac_lib_inference_addon_llama5cache6LedgerEb",
+            "__ZNK30qvac_lib_inference_addon_llama11speculative19SpeculativeFitModel9addMemoryEPKcRK18llama_model_paramsRK20llama_context_paramsRKNSt3__16vectorIP19ggml_backend_deviceNSA_9allocatorISD_EEEERNSB_I25common_device_memory_dataNSE_ISJ_EEEE",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler15StepUnlockGuardD1Ev",
             "__ZN26LlamaLazyInitializeBackend10initializeERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEES8_",
             "__ZNK13ModelMetaData9tryGetU32EPKc",

package/prebuilds/ios-x64-simulator/qvac__llm-llamacpp.bare.exports

@@ -7,7 +7,7 @@
     ],
     "current_versions": [
       {
-        "version": "0.64.2"
+        "version": "0.64.3"
       }
     ],
     "exported_symbols": [
@@ -467,9 +467,9 @@
             "__ZTSZN30qvac_lib_inference_addon_llama9assessFitEP8js_env_sP18js_callback_info_sEUlvE_",
             "__ZTSNSt3__111__match_anyIcEE",
             "__ZTSN28qvac_lib_inference_addon_cpp17MultiJobSchedulerE",
-            "__ZTSNSt3__120__shared_ptr_emplaceIN28qvac_lib_inference_addon_cpp16OutputCallBackJs5StateENS_9allocatorIS3_EEEE",
             "__ZTSZN28qvac_lib_inference_addon_cpp17makeQueueCallbackIN24llama_finetuning_helpers21FinetuneProgressStatsEEENSt3__18functionIFvRKT_EEENS3_10shared_ptrINS_11OutputQueueEEENS3_13shared_futureIyEEEUlRKS2_E_",
             "__ZTSNSt3__110__function6__funcIZN28qvac_lib_inference_addon_cpp2js11JsAsyncTask3runIZNS2_7AddonJs9cancelJobENS_8optionalIyEEEUlvE_EEP10js_value_sP8js_env_sOT_EUlSD_RKNS_9monostateEE_NS_9allocatorISJ_EEFSB_SD_SI_EEE",
+            "__ZTSNSt3__120__shared_ptr_emplaceIN28qvac_lib_inference_addon_cpp16OutputCallBackJs5StateENS_9allocatorIS3_EEEE",
             "__ZTI10LlmContext",
             "__ZTINSt3__110__function6__baseIFP10js_value_sRKNS_6vectorINS_12basic_stringIcNS_11char_traitsIcEENS_9allocatorIcEEEENS8_ISA_EEEEEEE",
             "__ZTSNSt3__120__shared_ptr_emplaceIN28qvac_lib_inference_addon_cpp9out_handl20JsErrorOutputHandlerENS_9allocatorIS3_EEEE",
@@ -591,7 +591,6 @@
             "__ZN14MtmdLlmContext17removeLastNTokensEi",
             "__ZN30qvac_lib_inference_addon_llama11speculative18SpeculativeRuntimeD2Ev",
             "__ZN30qvac_lib_inference_addon_llama5utils17resolveToolChoiceERKNSt3__18optionalINS1_12basic_stringIcNS1_11char_traitsIcEENS1_9allocatorIcEEEEEERKNS1_6vectorI16common_chat_toolNS6_ISD_EEEE",
-            "__ZNK30qvac_lib_inference_addon_llama11speculative19SpeculativeFitModel9addMemoryEjRKNSt3__16vectorIP19ggml_backend_deviceNS2_9allocatorIS5_EEEERNS3_I25common_device_memory_dataNS6_ISB_EEEE",
             "__ZN14MtmdLlmContext10resetMediaEv",
             "__ZN30qvac_lib_inference_addon_llama8batching22finalizeTerminalDriverER14SequenceDriverNS0_10StopReasonEbRKNSt3__18functionIFvRKNS4_12basic_stringIcNS4_11char_traitsIcEENS4_9allocatorIcEEEEEEE",
             "__ZN30qvac_lib_inference_addon_llama5utils21SequenceStateSnapshot10adoptEmptyEi",
@@ -681,7 +680,6 @@
             "__ZN14TextLlmContextC2ER13common_paramsNSt3__110unique_ptrI18common_init_resultNS2_14default_deleteIS4_EEEENS3_IN30qvac_lib_inference_addon_llama11speculative18SpeculativeRuntimeENS5_ISA_EEEE",
             "__ZN14TextLlmContext17beginCacheRequestEv",
             "__ZNK12CacheManager15isCacheDisabledEv",
-            "__ZN30qvac_lib_inference_addon_llama11speculative20fitLeavesOutMtpDraftERKNS0_9GgufShapeE",
             "__ZThn48_NK14TextLlmContext19residentStateTokensEv",
             "__ZN14MtmdLlmContext18commitCacheRequestEv",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler23recordPendingSlotCancelEjy",
@@ -1083,6 +1081,7 @@
             "__ZN10LlamaModel21isMultiBatchActivatedERNS_15ReloadableStateE",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchSchedulerC2E15LlmModelContextjjmiRK13common_paramsNSt3__18functionIFNS6_10unique_ptrI14SequenceDriverNS6_14default_deleteIS9_EEEES5_jiEEE",
             "__ZN14MtmdLlmContext15reconcilePromptE11PrefillPlanRKN30qvac_lib_inference_addon_llama5cache6LedgerEb",
+            "__ZNK30qvac_lib_inference_addon_llama11speculative19SpeculativeFitModel9addMemoryEPKcRK18llama_model_paramsRK20llama_context_paramsRKNSt3__16vectorIP19ggml_backend_deviceNSA_9allocatorISD_EEEERNSB_I25common_device_memory_dataNSE_ISJ_EEEE",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler15StepUnlockGuardD1Ev",
             "__ZN26LlamaLazyInitializeBackend10initializeERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEES8_",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler19drainFinishedLockedEPNSt3__111unique_lockINS2_5mutexEEE",