lemonade-sdk 8.0.4__py3-none-any.whl → 8.0.5__py3-none-any.whl

{lemonade_sdk-8.0.4.dist-info → lemonade_sdk-8.0.5.dist-info}/RECORD

@@ -1,19 +1,20 @@
 lemonade/__init__.py,sha256=W1Qk7r0rnQqFhPNHp6BIBT_q-OH3s-8Q_POoVfAmKW0,117
-lemonade/api.py,sha256=X7DxBgsOl5L_z6uTkwoJWf8x0rjXWS2JoeEqmo9bMfc,3873
+lemonade/api.py,sha256=kGz8N_9TuN3peFG8fES0odN0bWR9itLNomlR-FC2z8k,5515
 lemonade/cache.py,sha256=djr2qgyUUAWlQv8FehU9qlNtCwK0IZqo82hcBDyZ3-A,2850
 lemonade/cli.py,sha256=9Pcs3PcrWC2F8_pcBaz09xHUICIJTvpemBdPGyXkjIk,4395
 lemonade/sequence.py,sha256=KSH7BPsiyDKsOsg_ziQKEGsDwMmuO_YbgPRBxkZd0pw,13267
 lemonade/state.py,sha256=sdSezla7Cd7KYL90xY3p9kcNV4ndSyN6UvNLOr3vBMA,5261
-lemonade/version.py,sha256=8H4GfArMIlRTCgSsTERRXsD3PA6Y67z17oTQOJnuUME,22
+lemonade/version.py,sha256=obOXkQD52zgzH-mM2spS6LQ-gEWkuaiGpNTM_ISH0D8,22
 lemonade/common/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 lemonade/common/build.py,sha256=zTb0m1-kuUx6zw5QHp2SNnVuN6jOTMQ2FCdj9iH374U,6140
 lemonade/common/cli_helpers.py,sha256=hjBfXrTtFl8gmCFlL-ksviXR0mOcdPtTWVNKoEp3PG4,4993
 lemonade/common/exceptions.py,sha256=w83sVKmL1QXoJlGjj_bRyjIBMhlMqdVQy_FEOTu2YQI,2050
 lemonade/common/filesystem.py,sha256=QV3cHhKNu-7W2rr8wZ4JQfD2rP_5T2Js7jiDQBYWHVQ,12142
+lemonade/common/inference_engines.py,sha256=lcmir_pATr71TfSBJoIZEi3G9xyxNwi2_xpPvPD8_xI,12932
 lemonade/common/network.py,sha256=EkWTxjJ-UM469nEJdzEl-5UNO7dPfVfFzU2SVMMPaD0,1425
 lemonade/common/printing.py,sha256=GFFzrXIineIOMa9yu0lo5sL4j6A5BBg_T9aUCdP-juw,3229
 lemonade/common/status.py,sha256=xSOZN508cdRtrs1HVyr9zmASYg69EsZBLSs0lroLoCM,16519
-lemonade/common/system_info.py,sha256=qOwteG_mBo-ImilbiK7Gq37sWIE9ugF0dbWcj9zLD40,12234
+lemonade/common/system_info.py,sha256=dOtX8WLHCz1xmURZWnqhDbyNZv_AulrpX_bbI58eHFQ,27084
 lemonade/common/test_helpers.py,sha256=Gwk-pa_6xYAo2oro-2EJNfuouAfw8k_brCbcMC-E-r0,758
 lemonade/profilers/__init__.py,sha256=JKVonvJ4XZ9_6sKXPWsiMLQCNyzQOxhQw5BEHR1qOfU,31
 lemonade/profilers/memory_tracker.py,sha256=1iuKt0FmNVYLDnOc-oZM8dX9TUksvoxO0m2EoYWjhYQ,9367
@@ -23,7 +24,7 @@ lemonade/tools/accuracy.py,sha256=9HCmczDngkBUuUrt49d2CkRo4J0qyWoFYs5cj20bGkg,11
 lemonade/tools/adapter.py,sha256=HG54iMd6HDPZ4vnQIl7codq3HzffWbcHSIs_jVbNbhU,2958
 lemonade/tools/bench.py,sha256=aN5LMA_EH6-ZhAH3Gf26JYL7s0eKpUd3j-bReRhzvEY,10016
 lemonade/tools/humaneval.py,sha256=JbxuoOzvR4iyxZv4R6MI7a3gUt5ef_Jj6Ie-9VP2wzY,9531
-lemonade/tools/management_tools.py,sha256=RO-lU-hjZhrP9KD9qcLI7MrLu-Rxnkrxzn45qqwKInE,8554
+lemonade/tools/management_tools.py,sha256=U8GaJnjdXyQ9sw8UxBQMc7glpaLciaVphASaQS4kJsA,10202
 lemonade/tools/mmlu.py,sha256=c2QaIMDzjqxCvgHlMXmy_dP1sAFkwkDxL7RO2nogI6s,11071
 lemonade/tools/perplexity.py,sha256=eiaTZ3yhqF2pfwOffVbKKJLwjSri7Im2pC-tBJr7LLU,5638
 lemonade/tools/prompt.py,sha256=cy6McZeLgk26xG1dJEY-cYnY2x8FUdyOOSG86WfBKCg,9348
@@ -45,26 +46,26 @@ lemonade/tools/report/llm_report.py,sha256=bVHhwCINA-Ok2EdSwAsLubsc83N3KWOVuwTgu
 lemonade/tools/report/table.py,sha256=wJFzKtlmGQH0RQ5O9nevtpMe_-zQ-8zNOndINQuzsjM,27793
 lemonade/tools/server/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 lemonade/tools/server/llamacpp.py,sha256=e1MYKSJBu-jlOE5GQSBsC9CUPAeqw5wXXxoxBKA5zb8,20038
-lemonade/tools/server/serve.py,sha256=ORffC4bcBJ-L5-JbmZX91X3yHt1JWxZcIjrZuu9x8TQ,56165
+lemonade/tools/server/serve.py,sha256=Pp_w4iuRMkpJLF-XrTsBIBrSNBQIOl8PRZC_Cj4URnU,57334
 lemonade/tools/server/tool_calls.py,sha256=xrAlQwKG-nv2xLlf8f9CDSaUbyMn8ZtHkds9iZLG9K8,5230
 lemonade/tools/server/tray.py,sha256=4Kf3x8YfRaItPW7lxlEwerD7c5Q2snzcNk3ZrEoae58,17259
 lemonade/tools/server/webapp.py,sha256=8Das5yXOaSBLZmSZ_eddJajQFxBhvl5D6GI_hHlGbE0,1040
 lemonade/tools/server/static/favicon.ico,sha256=hMmP9qGJNeZ0mFS86JIqPbZstXMZn0Z76_HfHQpREAU,126745
-lemonade/tools/server/static/styles.css,sha256=x-pf7xts0te9JWAafcNFqzE7r1fl6n_H362Eiz49ixI,24722
-lemonade/tools/server/static/webapp.html,sha256=AS61ZBDnZkIUpT-iZFlTnWpkp6Yeozs4obzauX4crlU,35004
+lemonade/tools/server/static/styles.css,sha256=jXFPIHPrhRz_CJyRJrYusAECSDTO00sKUu7ajrQgFuA,24655
+lemonade/tools/server/static/webapp.html,sha256=tmwASvULb3d2_NfHEH9rKbEEJl3D7ygXjaCLVYkyWbg,35969
 lemonade/tools/server/utils/port.py,sha256=XnIg2qS73QRrsJn6LgHcrJPmku30Tv6vsYcBVMj82K4,2186
 lemonade/tools/server/utils/system_tray.py,sha256=b9lvNv9chJKQxvmH7qzAuUe6H9HsLu7pdHFqGlAJaL0,12654
 lemonade/tools/server/utils/thread.py,sha256=pK9K_6DNWoQ78NArkAX3Ym2WsxLnCs9sKTk6TitlYnI,2804
 lemonade_install/__init__.py,sha256=26zohKg2jgr_5y7tObduWMYQg8zCTWMZHL8lfi2zZVQ,40
 lemonade_install/install.py,sha256=DJWR36QSjZtvEwRjYPNSjhYgoxLjI_6OPrCMZjL0ChY,28263
-lemonade_sdk-8.0.4.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-lemonade_sdk-8.0.4.dist-info/licenses/NOTICE.md,sha256=B8lEqi4QE41J9ljz4Riv2JgHD1v8GCZE6nNBHO3KIA0,2135
-lemonade_server/cli.py,sha256=z6ojwFaOIz0hbUbVtZWMLP4YDpkcVOmqwmdm55dhKA4,11980
+lemonade_sdk-8.0.5.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+lemonade_sdk-8.0.5.dist-info/licenses/NOTICE.md,sha256=B8lEqi4QE41J9ljz4Riv2JgHD1v8GCZE6nNBHO3KIA0,2135
+lemonade_server/cli.py,sha256=2Un5uLK04fIxlfcTiZ0T_EWbbaq2tYymkUHNFeuvB7g,16041
 lemonade_server/model_manager.py,sha256=0HqLR38uOu_hxRWVYQ_P6YmwaR-jkDuaAqGYo60X8C0,16702
 lemonade_server/pydantic_models.py,sha256=rp_FFhoTwg6jNmgol-kShwffnRDGbt7jTbIeELvgOIo,2876
 lemonade_server/server_models.json,sha256=Y-j9KAvHmfv77welC0rfRao4inLBce6AVySb-oy_uNE,7519
-lemonade_sdk-8.0.4.dist-info/METADATA,sha256=FqA9Jtgx1QE1EjLg_lxcfcAMI3j0cKpZxoe4GnaGLRA,7754
-lemonade_sdk-8.0.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-lemonade_sdk-8.0.4.dist-info/entry_points.txt,sha256=gJppn0ETtXXR6ceKWEIRdk42kMC7ps59EmU3NCPyPUk,144
-lemonade_sdk-8.0.4.dist-info/top_level.txt,sha256=10ap5GNiPhalO4V50LRoxA1FqRT9g3Xkia6BITu880k,42
-lemonade_sdk-8.0.4.dist-info/RECORD,,
+lemonade_sdk-8.0.5.dist-info/METADATA,sha256=e2w0jPyEnyk-SeLAbYZgeGldq-2CQHm9Hly_mQgZ8uo,15224
+lemonade_sdk-8.0.5.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+lemonade_sdk-8.0.5.dist-info/entry_points.txt,sha256=gJppn0ETtXXR6ceKWEIRdk42kMC7ps59EmU3NCPyPUk,144
+lemonade_sdk-8.0.5.dist-info/top_level.txt,sha256=10ap5GNiPhalO4V50LRoxA1FqRT9g3Xkia6BITu880k,42
+lemonade_sdk-8.0.5.dist-info/RECORD,,

lemonade_server/cli.py

@@ -27,43 +27,75 @@ class DeleteError(Exception):
     """
 
 
+class ServerTimeoutError(Exception):
+    """
+    The server failed to start within the timeout period
+    """
+
+
+class ModelNotAvailableError(Exception):
+    """
+    The specified model is not available on the server
+    """
+
+
 def serve(
-    port: int,
+    port: int = None,
     log_level: str = None,
     tray: bool = False,
+    use_thread: bool = False,
 ):
     """
     Execute the serve command
     """
 
-    # Check if Lemonade Server is already running
-    _, running_port = get_server_info()
-    if running_port is not None:
-        print(
-            (
-                f"Lemonade Server is already running on port {running_port}\n"
-                "Please stop the existing server before starting a new instance."
-            ),
-        )
-        sys.exit(ExitCodes.SERVER_ALREADY_RUNNING)
-
     # Otherwise, start the server
     print("Starting Lemonade Server...")
     from lemonade.tools.server.serve import Server, DEFAULT_PORT, DEFAULT_LOG_LEVEL
 
-    server = Server()
     port = port if port is not None else DEFAULT_PORT
     log_level = log_level if log_level is not None else DEFAULT_LOG_LEVEL
 
     # Hidden environment variable to enable input truncation (experimental feature)
     truncate_inputs = "LEMONADE_TRUNCATE_INPUTS" in os.environ
 
-    server.run(
-        port=port,
-        log_level=log_level,
-        truncate_inputs=truncate_inputs,
-        tray=tray,
-    )
+    # Start the server
+    serve_kwargs = {
+        "log_level": log_level,
+        "truncate_inputs": truncate_inputs,
+        "tray": tray,
+    }
+    server = Server()
+    if not use_thread:
+        server.run(
+            port=port,
+            **serve_kwargs,
+        )
+    else:
+        from threading import Thread
+        import time
+
+        # Start a background thread to run the server
+        server_thread = Thread(
+            target=server.run,
+            args=(port,),
+            kwargs=serve_kwargs,
+            daemon=True,
+        )
+        server_thread.start()
+
+        # Wait for the server to be ready
+        max_wait_time = 30
+        wait_interval = 0.5
+        waited = 0
+        while waited < max_wait_time:
+            time.sleep(wait_interval)
+            _, running_port = get_server_info()
+            if running_port is not None:
+                break
+            waited += wait_interval
+
+        return port, server_thread
 
 
 def stop():
@@ -161,9 +193,8 @@ def pull(
             if pull_response.status_code != 200:
                 raise PullError(
                     f"Failed to install {model_name}. Check the "
-                    "Lemonade Server log for more information. A list of supported models "
-                    "is provided at "
-                    "https://github.com/lemonade-sdk/lemonade/blob/main/docs/server/server_models.md"
+                    "Lemonade Server log for more information. You can list "
+                    "supported models with `lemonade-server list`"
                 )
     else:
         from lemonade_server.model_manager import ModelManager
@@ -212,6 +243,53 @@ def delete(model_names: List[str]):
             ModelManager().delete_model(model_name)
 
 
+def run(model_name: str):
+    """
+    Start the server if not running and open the webapp with the specified model
+    """
+    import webbrowser
+    import time
+
+    # Start the server if not running
+    _, port = get_server_info()
+    server_previously_running = port is not None
+    if not server_previously_running:
+        port, server_thread = serve(use_thread=True, tray=True, log_level="info")
+
+    # Pull model
+    pull([model_name])
+
+    # Load model
+    load(model_name, port)
+
+    # Open the webapp with the specified model
+    url = f"http://localhost:{port}/?model={model_name}#llm-chat"
+    print(f"You can now chat with {model_name} at {url}")
+    webbrowser.open(url)
+
+    # Keep the server running if we started it
+    if not server_previously_running:
+        while server_thread.is_alive():
+            time.sleep(0.5)
+
+
+def load(model_name: str, port: int):
+    """
+    Load a model using the endpoint
+    """
+    import requests
+
+    base_url = f"http://localhost:{port}/api/v1"
+
+    # Load the model
+    load_response = requests.post(f"{base_url}/load", json={"model_name": model_name})
+    if load_response.status_code != 200:
+        raise ModelLoadError(
+            f"Failed to load {model_name}. Check the "
+            "Lemonade Server log for more information."
+        )
+
+
 def version():
     """
     Print the version number
@@ -294,6 +372,46 @@ def get_server_info() -> Tuple[int | None, int | None]:
     return None, None
 
 
+def list_models():
+    """
+    List recommended models and their download status
+    """
+    from tabulate import tabulate
+    from lemonade_server.model_manager import ModelManager
+
+    model_manager = ModelManager()
+
+    # Get all supported models and downloaded models
+    supported_models = model_manager.supported_models
+    downloaded_models = model_manager.downloaded_models
+
+    # Filter to only show recommended models
+    recommended_models = {
+        model_name: model_info
+        for model_name, model_info in supported_models.items()
+        if model_info.get("suggested", False)
+    }
+
+    # Create table data
+    table_data = []
+    for model_name, model_info in recommended_models.items():
+        downloaded_status = "Yes" if model_name in downloaded_models else "No"
+
+        # Get model labels/type
+        labels = model_info.get("labels", [])
+        model_type = ", ".join(labels) if labels else "-"
+
+        table_data.append([model_name, downloaded_status, model_type])
+
+    # Sort by model name for consistent display
+    # Show downloaded models first
+    table_data.sort(key=lambda x: (x[1] == "No", x[0].lower()))
+
+    # Display table
+    headers = ["Model Name", "Downloaded", "Details"]
+    print(tabulate(table_data, headers=headers, tablefmt="simple"))
+
+
 def main():
     parser = argparse.ArgumentParser(
         description="Serve LLMs on CPU, GPU, and NPU.",
@@ -333,6 +451,11 @@ def main():
     # Stop command
     stop_parser = subparsers.add_parser("stop", help="Stop the server")
 
+    # List command
+    list_parser = subparsers.add_parser(
+        "list", help="List recommended models and their download status"
+    )
+
     # Pull command
     pull_parser = subparsers.add_parser(
         "pull",
@@ -381,6 +504,16 @@ def main():
         nargs="+",
     )
 
+    # Run command
+    run_parser = subparsers.add_parser(
+        "run",
+        help="Chat with specified model (starts server if needed)",
+    )
+    run_parser.add_argument(
+        "model",
+        help="Lemonade Server model name to run",
+    )
+
     args = parser.parse_args()
 
     if os.name != "nt":
@@ -389,6 +522,15 @@ def main():
     if args.version:
         version()
     elif args.command == "serve":
+        _, running_port = get_server_info()
+        if running_port is not None:
+            print(
+                (
+                    f"Lemonade Server is already running on port {running_port}\n"
+                    "Please stop the existing server before starting a new instance."
+                ),
+            )
+            sys.exit(ExitCodes.SERVER_ALREADY_RUNNING)
         serve(
             port=args.port,
             log_level=args.log_level,
@@ -396,6 +538,8 @@ def main():
         )
     elif args.command == "status":
         status()
+    elif args.command == "list":
+        list_models()
     elif args.command == "pull":
         pull(
             args.model,
@@ -408,6 +552,8 @@ def main():
         delete(args.model)
     elif args.command == "stop":
         stop()
+    elif args.command == "run":
+        run(args.model)
     elif args.command == "help" or not args.command:
         parser.print_help()
 

lemonade_sdk-8.0.4.dist-info/METADATA

@@ -1,176 +0,0 @@
-Metadata-Version: 2.4
-Name: lemonade-sdk
-Version: 8.0.4
-Summary: Lemonade SDK: Your LLM Aide for Validation and Deployment
-Author-email: lemonade@amd.com
-Requires-Python: >=3.10, <3.12
-Description-Content-Type: text/markdown
-License-File: LICENSE
-License-File: NOTICE.md
-Requires-Dist: invoke>=2.0.0
-Requires-Dist: onnx<1.18.0,>=1.11.0
-Requires-Dist: pyyaml>=5.4
-Requires-Dist: typeguard>=2.3.13
-Requires-Dist: packaging>=20.9
-Requires-Dist: numpy<2.0.0
-Requires-Dist: fasteners
-Requires-Dist: GitPython>=3.1.40
-Requires-Dist: psutil>=6.1.1
-Requires-Dist: wmi
-Requires-Dist: py-cpuinfo
-Requires-Dist: pytz
-Requires-Dist: zstandard
-Requires-Dist: fastapi
-Requires-Dist: uvicorn[standard]
-Requires-Dist: openai>=1.81.0
-Requires-Dist: transformers<=4.51.3
-Requires-Dist: jinja2
-Requires-Dist: tabulate
-Requires-Dist: sentencepiece
-Requires-Dist: huggingface-hub==0.33.0
-Provides-Extra: oga-hybrid
-Requires-Dist: onnx==1.16.1; extra == "oga-hybrid"
-Requires-Dist: numpy==1.26.4; extra == "oga-hybrid"
-Requires-Dist: protobuf>=6.30.1; extra == "oga-hybrid"
-Provides-Extra: oga-cpu
-Requires-Dist: onnxruntime-genai==0.8.2; extra == "oga-cpu"
-Requires-Dist: onnxruntime>=1.22.0; extra == "oga-cpu"
-Provides-Extra: dev
-Requires-Dist: torch>=2.6.0; extra == "dev"
-Requires-Dist: accelerate; extra == "dev"
-Requires-Dist: datasets; extra == "dev"
-Requires-Dist: pandas>=1.5.3; extra == "dev"
-Requires-Dist: matplotlib; extra == "dev"
-Requires-Dist: human-eval-windows==1.0.4; extra == "dev"
-Requires-Dist: lm-eval[api]; extra == "dev"
-Provides-Extra: oga-hybrid-minimal
-Requires-Dist: lemonade-sdk[oga-hybrid]; extra == "oga-hybrid-minimal"
-Provides-Extra: oga-cpu-minimal
-Requires-Dist: lemonade-sdk[oga-cpu]; extra == "oga-cpu-minimal"
-Provides-Extra: llm
-Requires-Dist: lemonade-sdk[dev]; extra == "llm"
-Provides-Extra: llm-oga-cpu
-Requires-Dist: lemonade-sdk[dev,oga-cpu]; extra == "llm-oga-cpu"
-Provides-Extra: llm-oga-igpu
-Requires-Dist: onnxruntime-genai-directml==0.6.0; extra == "llm-oga-igpu"
-Requires-Dist: onnxruntime-directml<1.22.0,>=1.19.0; extra == "llm-oga-igpu"
-Requires-Dist: transformers<4.45.0; extra == "llm-oga-igpu"
-Requires-Dist: lemonade-sdk[dev]; extra == "llm-oga-igpu"
-Provides-Extra: llm-oga-cuda
-Requires-Dist: onnxruntime-genai-cuda==0.8.2; extra == "llm-oga-cuda"
-Requires-Dist: onnxruntime-gpu>=1.22.0; extra == "llm-oga-cuda"
-Requires-Dist: transformers<=4.51.3; extra == "llm-oga-cuda"
-Requires-Dist: lemonade-sdk[dev]; extra == "llm-oga-cuda"
-Provides-Extra: llm-oga-npu
-Requires-Dist: onnx==1.16.0; extra == "llm-oga-npu"
-Requires-Dist: onnxruntime==1.18.0; extra == "llm-oga-npu"
-Requires-Dist: numpy==1.26.4; extra == "llm-oga-npu"
-Requires-Dist: protobuf>=6.30.1; extra == "llm-oga-npu"
-Requires-Dist: lemonade-sdk[dev]; extra == "llm-oga-npu"
-Provides-Extra: llm-oga-hybrid
-Requires-Dist: lemonade-sdk[dev,oga-hybrid]; extra == "llm-oga-hybrid"
-Provides-Extra: llm-oga-unified
-Requires-Dist: lemonade-sdk[llm-oga-hybrid]; extra == "llm-oga-unified"
-Dynamic: author-email
-Dynamic: description
-Dynamic: description-content-type
-Dynamic: license-file
-Dynamic: provides-extra
-Dynamic: requires-dist
-Dynamic: requires-python
-Dynamic: summary
-
-[![Lemonade tests](https://github.com/lemonade-sdk/lemonade/actions/workflows/test_lemonade.yml/badge.svg)](https://github.com/lemonade-sdk/lemonade/tree/main/test "Check out our tests")
-[![OS - Windows | Linux](https://img.shields.io/badge/OS-windows%20%7C%20linux-blue)](docs/README.md#installation "Check out our instructions")
-[![Made with Python](https://img.shields.io/badge/Python-3.10-blue?logo=python&logoColor=white)](docs/README.md#installation "Check out our instructions")
-
-## 🍋 Lemonade SDK: Quickly serve, benchmark and deploy LLMs
-
-The [Lemonade SDK](./docs/README.md) makes it easy to run Large Language Models (LLMs) on your PC. Our focus is using the best tools, such as neural processing units (NPUs) and Vulkan GPU acceleration, to maximize LLM speed and responsiveness.
-
-<div align="center">
-  <img src="https://download.amd.com/images/lemonade_640x480_1.gif" alt="Lemonade Demo" title="Lemonade in Action">
-</div>
-
-### Features
-
-The [Lemonade SDK](./docs/README.md) is comprised of the following:
-
-- 🌐 **[Lemonade Server](https://lemonade-server.ai/docs)**: A local LLM server for running ONNX and GGUF models using the OpenAI API standard. Install and enable your applications with NPU and GPU acceleration in minutes.
-- 🐍 **[Lemonade API](./docs/lemonade_api.md)**: High-level Python API to directly integrate Lemonade LLMs into Python applications.
-- 🖥️ **[Lemonade CLI](./docs/dev_cli/README.md)**: The `lemonade` CLI lets you mix-and-match LLMs (ONNX, GGUF, SafeTensors) with measurement tools to characterize your models on your hardware. The available tools are:
-  - Prompting with templates.
-  - Measuring accuracy with a variety of tests.
-  - Benchmarking to get the time-to-first-token and tokens per second.
-  - Profiling the memory utilization.
-
-### [Click here to get started with Lemonade.](./docs/README.md)
-
-### Supported Configurations
-
-Maximum LLM performance requires the right hardware accelerator with the right inference engine for your scenario. Lemonade supports the following configurations, while also making it easy to switch between them at runtime.
-
-<table border="1" cellpadding="6" cellspacing="0">
-  <thead>
-    <tr>
-      <th rowspan="2">Hardware</th>
-      <th colspan="3" align="center">🛠️ Engine Support</th>
-      <th colspan="2" align="center">🖥️ OS (x86/x64)</th>
-    </tr>
-    <tr>
-      <th align="center">OGA</th>
-      <th align="center">llamacpp</th>
-      <th align="center">HF</th>
-      <th align="center">Windows</th>
-      <th align="center">Linux</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <td>🧠 CPU</td>
-      <td align="center">All platforms</td>
-      <td align="center">All platforms</td>
-      <td align="center">All platforms</td>
-      <td align="center">✅</td>
-      <td align="center">✅</td>
-    </tr>
-    <tr>
-      <td>🎮 GPU</td>
-      <td align="center">—</td>
-      <td align="center">Vulkan: All platforms<br><small>Focus:<br/>Ryzen™ AI 7000/8000/300<br/>Radeon™ 7000/9000</small></td>
-      <td align="center">—</td>
-      <td align="center">✅</td>
-      <td align="center">✅</td>
-    </tr>
-    <tr>
-      <td>🤖 NPU</td>
-      <td align="center">AMD Ryzen™ AI 300 series</td>
-      <td align="center">—</td>
-      <td align="center">—</td>
-      <td align="center">✅</td>
-      <td align="center">—</td>
-    </tr>
-  </tbody>
-</table>
-
-To learn more about the supported hardware and software, visit the documentation [here](./docs/README.md#software-and-hardware-overview).
-
-## Integrate Lemonade Server with Your Application
-
-Lemonade Server enables languages including Python, C++, Java, C#, Node.js, Go, Ruby, Rust, and PHP. For the full list and integration details, see [docs/server/README.md](./docs/server/README.md).
-
-## Contributing
-
-We are actively seeking collaborators from across the industry. If you would like to contribute to this project, please check out our [contribution guide](./docs/contribute.md).
-
-## Maintainers
-
-This project is sponsored by AMD. It is maintained by @danielholanda @jeremyfowers @ramkrishna @vgodsoe in equal measure. You can reach us by filing an [issue](https://github.com/lemonade-sdk/lemonade/issues) or email [lemonade@amd.com](mailto:lemonade@amd.com).
-
-## License
-
-This project is licensed under the [Apache 2.0 License](https://github.com/lemonade-sdk/lemonade/blob/main/LICENSE). Portions of the project are licensed as described in [NOTICE.md](./NOTICE.md).
-
-<!--This file was originally licensed under Apache 2.0. It has been modified.
-Modifications Copyright (c) 2025 AMD-->
-