fix mlx llm bundling

backend/build_binary.py

@@ -373,10 +373,16 @@ def build_server(cuda=False):
                 "mlx_audio.tts",
                 "--hidden-import",
                 "mlx_audio.stt",
+                "--hidden-import",
+                "mlx_lm",
+                "--hidden-import",
+                "backend.backends.qwen_llm_backend",
                 "--collect-submodules",
                 "mlx",
                 "--collect-submodules",
                 "mlx_audio",
+                "--collect-submodules",
+                "mlx_lm",
                 # Use --collect-all so PyInstaller bundles both data files AND
                 # native shared libraries (.dylib, .metallib) for MLX.
                 # Previously only --collect-data was used, which caused MLX to
@@ -386,6 +392,11 @@ def build_server(cuda=False):
                 "mlx",
                 "--collect-all",
                 "mlx_audio",
+                # mlx_lm ships chat_templates/ JSON files and loads tool_parsers
+                # submodules dynamically via importlib at tokenizer load time,
+                # which --hidden-import alone can't resolve.
+                "--collect-all",
+                "mlx_lm",
             ]
         )
     elif not cuda:
@@ -506,6 +517,8 @@ def build_shim():
         "--exclude-module",
         "mlx_audio",
         "--exclude-module",
+        "mlx_lm",
+        "--exclude-module",
         "qwen_tts",
         "--exclude-module",
         "chatterbox",

backend/voicebox-server.spec

@@ -5,7 +5,7 @@ from PyInstaller.utils.hooks import copy_metadata
 
 datas = []
 binaries = []
-hiddenimports = ['backend', 'backend.main', 'backend.config', 'backend.database', 'backend.models', 'backend.services.profiles', 'backend.services.history', 'backend.services.tts', 'backend.services.transcribe', 'backend.utils.platform_detect', 'backend.backends', 'backend.backends.pytorch_backend', 'backend.backends.qwen_custom_voice_backend', 'backend.utils.audio', 'backend.utils.cache', 'backend.utils.progress', 'backend.utils.hf_progress', 'backend.services.cuda', 'backend.services.effects', 'backend.utils.effects', 'backend.services.versions', 'pedalboard', 'chatterbox', 'chatterbox.tts_turbo', 'chatterbox.mtl_tts', 'backend.backends.chatterbox_backend', 'backend.backends.chatterbox_turbo_backend', 'backend.backends.luxtts_backend', 'zipvoice', 'zipvoice.luxvoice', 'torch', 'transformers', 'fastapi', 'uvicorn', 'sqlalchemy', 'soundfile', 'qwen_tts', 'qwen_tts.inference', 'qwen_tts.inference.qwen3_tts_model', 'qwen_tts.inference.qwen3_tts_tokenizer', 'qwen_tts.core', 'qwen_tts.cli', 'requests', 'pkg_resources.extern', 'backend.backends.hume_backend', 'tada', 'tada.modules', 'tada.modules.tada', 'tada.modules.encoder', 'tada.modules.decoder', 'tada.modules.aligner', 'tada.modules.acoustic_spkr_verf', 'tada.nn', 'tada.nn.vibevoice', 'tada.utils', 'tada.utils.gray_code', 'tada.utils.text', 'backend.utils.dac_shim', 'torchaudio', 'backend.backends.kokoro_backend', 'en_core_web_sm', 'loguru', 'backend.mcp_server', 'backend.mcp_server.server', 'backend.mcp_server.tools', 'backend.mcp_server.context', 'backend.mcp_server.resolve', 'backend.mcp_server.events', 'sse_starlette', 'backend.backends.mlx_backend', 'mlx', 'mlx.core', 'mlx.nn', 'mlx_audio', 'mlx_audio.tts', 'mlx_audio.stt']
+hiddenimports = ['backend', 'backend.main', 'backend.config', 'backend.database', 'backend.models', 'backend.services.profiles', 'backend.services.history', 'backend.services.tts', 'backend.services.transcribe', 'backend.utils.platform_detect', 'backend.backends', 'backend.backends.pytorch_backend', 'backend.backends.qwen_custom_voice_backend', 'backend.utils.audio', 'backend.utils.cache', 'backend.utils.progress', 'backend.utils.hf_progress', 'backend.services.cuda', 'backend.services.effects', 'backend.utils.effects', 'backend.services.versions', 'pedalboard', 'chatterbox', 'chatterbox.tts_turbo', 'chatterbox.mtl_tts', 'backend.backends.chatterbox_backend', 'backend.backends.chatterbox_turbo_backend', 'backend.backends.luxtts_backend', 'zipvoice', 'zipvoice.luxvoice', 'torch', 'transformers', 'fastapi', 'uvicorn', 'sqlalchemy', 'soundfile', 'qwen_tts', 'qwen_tts.inference', 'qwen_tts.inference.qwen3_tts_model', 'qwen_tts.inference.qwen3_tts_tokenizer', 'qwen_tts.core', 'qwen_tts.cli', 'requests', 'pkg_resources.extern', 'backend.backends.hume_backend', 'tada', 'tada.modules', 'tada.modules.tada', 'tada.modules.encoder', 'tada.modules.decoder', 'tada.modules.aligner', 'tada.modules.acoustic_spkr_verf', 'tada.nn', 'tada.nn.vibevoice', 'tada.utils', 'tada.utils.gray_code', 'tada.utils.text', 'backend.utils.dac_shim', 'torchaudio', 'backend.backends.kokoro_backend', 'en_core_web_sm', 'loguru', 'backend.mcp_server', 'backend.mcp_server.server', 'backend.mcp_server.tools', 'backend.mcp_server.context', 'backend.mcp_server.resolve', 'backend.mcp_server.events', 'sse_starlette', 'backend.backends.mlx_backend', 'mlx', 'mlx.core', 'mlx.nn', 'mlx_audio', 'mlx_audio.tts', 'mlx_audio.stt', 'mlx_lm', 'backend.backends.qwen_llm_backend']
 datas += copy_metadata('qwen-tts')
 datas += copy_metadata('requests')
 datas += copy_metadata('transformers')
@@ -18,6 +18,7 @@ hiddenimports += collect_submodules('jaraco')
 hiddenimports += collect_submodules('tada')
 hiddenimports += collect_submodules('mlx')
 hiddenimports += collect_submodules('mlx_audio')
+hiddenimports += collect_submodules('mlx_lm')
 tmp_ret = collect_all('spacy_pkuseg')
 datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
 tmp_ret = collect_all('zipvoice')
@@ -56,6 +57,8 @@ tmp_ret = collect_all('mlx')
 datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
 tmp_ret = collect_all('mlx_audio')
 datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
+tmp_ret = collect_all('mlx_lm')
+datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
 
 
 a = Analysis(