lemonade-sdk 8.0.0__py3-none-any.whl → 8.0.1__py3-none-any.whl

lemonade/tools/server/llamacpp.py

@@ -416,25 +416,43 @@ def chat_completion(
         exclude_unset=True, exclude_none=True
     )
 
-    def event_stream():
+    # Check if streaming is requested
+    if chat_completion_request.stream:
+
+        def event_stream():
+            try:
+                # Enable streaming
+                for chunk in client.chat.completions.create(**request_dict):
+                    yield f"data: {chunk.model_dump_json()}\n\n"
+                yield "data: [DONE]\n\n"
+
+                # Show telemetry after completion
+                telemetry.show_telemetry()
+
+            except Exception as e:  # pylint: disable=broad-exception-caught
+                yield f'data: {{"error": "{str(e)}"}}\n\n'
+
+        return StreamingResponse(
+            event_stream(),
+            media_type="text/event-stream",
+            headers={
+                "Cache-Control": "no-cache",
+                "Connection": "keep-alive",
+            },
+        )
+    else:
+        # Non-streaming response
         try:
-            # Enable streaming
-            request_dict["stream"] = True
-            for chunk in client.chat.completions.create(**request_dict):
-                yield f"data: {chunk.model_dump_json()}\n\n"
-            yield "data: [DONE]\n\n"
+            # Disable streaming for non-streaming requests
+            response = client.chat.completions.create(**request_dict)
 
             # Show telemetry after completion
             telemetry.show_telemetry()
 
+            return response
+
         except Exception as e:  # pylint: disable=broad-exception-caught
-            yield f'data: {{"error": "{str(e)}"}}\n\n'
-
-    return StreamingResponse(
-        event_stream(),
-        media_type="text/event-stream",
-        headers={
-            "Cache-Control": "no-cache",
-            "Connection": "keep-alive",
-        },
-    )
+            raise HTTPException(
+                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+                detail=f"Chat completion error: {str(e)}",
+            )

lemonade/tools/server/serve.py

@@ -29,6 +29,7 @@ from openai.types.chat.chat_completion_message_tool_call import (
     ChatCompletionMessageToolCall,
     Function,
 )
+from openai.types.completion_usage import CompletionUsage
 from openai.types.chat.chat_completion import Choice
 from openai.types.chat.chat_completion_chunk import (
     ChoiceDelta,
@@ -576,9 +577,16 @@ class Server(ManagementTool):
                 logprobs=logprobs,
             )
 
+            usage = CompletionUsage(
+                prompt_tokens=self.input_tokens,
+                completion_tokens=self.output_tokens,
+                total_tokens=self.input_tokens + self.output_tokens,
+            )
+
             return Completion(
                 id="0",
                 choices=[choice],
+                usage=usage,
                 model=self.llm_loaded.checkpoint,
                 object="text_completion",
                 created=int(time.time()),
@@ -773,9 +781,16 @@ class Server(ManagementTool):
                 logprobs=None,
             )
 
+            usage = CompletionUsage(
+                prompt_tokens=self.input_tokens,
+                completion_tokens=self.output_tokens,
+                total_tokens=self.input_tokens + self.output_tokens,
+            )
+
             return ChatCompletion(
                 id="0",
                 choices=[choice],
+                usage=usage,
                 model=self.llm_loaded.checkpoint,
                 object="chat.completion",
                 created=int(time.time()),

lemonade/version.py

@@ -1 +1 @@
-__version__ = "8.0.0"
+__version__ = "8.0.1"

{lemonade_sdk-8.0.0.dist-info → lemonade_sdk-8.0.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: lemonade-sdk
-Version: 8.0.0
+Version: 8.0.1
 Summary: Lemonade SDK: Your LLM Aide for Validation and Deployment
 Author-email: lemonade@amd.com
 Requires-Python: >=3.10, <3.12
@@ -133,7 +133,7 @@ Maximum LLM performance requires the right hardware accelerator with the right i
     <tr>
       <td>🎮 GPU</td>
       <td align="center">—</td>
-      <td align="center">Vulkan: All platforms<br><small>Focus: Radeon™ 7000/9000</small></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>
@@ -158,6 +158,10 @@ Maximum LLM performance requires the right hardware accelerator with the right i
 | **llamacpp** | Community-driven engine with strong GPU acceleration, support for thousands of `.gguf` models, and advanced features such as vision-language models (VLMs) and mixture-of-experts (MoEs). |
 | **Hugging Face (HF)** | Hugging Face's `transformers` library can run the original `.safetensors` trained weights for models on Meta's PyTorch engine, which provides a source of truth for accuracy measurement. |
 
+## 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).

{lemonade_sdk-8.0.0.dist-info → lemonade_sdk-8.0.1.dist-info}/RECORD

@@ -4,7 +4,7 @@ lemonade/cache.py,sha256=djr2qgyUUAWlQv8FehU9qlNtCwK0IZqo82hcBDyZ3-A,2850
 lemonade/cli.py,sha256=XzptHh6LTl5OdGRnxiLykQ8QBl2rQmhWH5w0KPJVyY4,4359
 lemonade/sequence.py,sha256=KSH7BPsiyDKsOsg_ziQKEGsDwMmuO_YbgPRBxkZd0pw,13267
 lemonade/state.py,sha256=sdSezla7Cd7KYL90xY3p9kcNV4ndSyN6UvNLOr3vBMA,5261
-lemonade/version.py,sha256=SWqJTEDnx2fOon29wQowBCNjEkhyhMbbqVsSu4EpdWI,22
+lemonade/version.py,sha256=qR-61NMOca8p2Rty8s6xwXQSXLDufw2os6i4zdyqfak,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
@@ -44,8 +44,8 @@ lemonade/tools/report/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3h
 lemonade/tools/report/llm_report.py,sha256=bVHhwCINA-Ok2EdSwAsLubsc83N3KWOVuwTguw7jDcE,6676
 lemonade/tools/report/table.py,sha256=di8IZkolt_kaZfWri6GQkhPE1zCELqcrBcG1x1fzWqg,24843
 lemonade/tools/server/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-lemonade/tools/server/llamacpp.py,sha256=U2eE9zfwE5sWUnS8A9oSf0Ak4v8dbjnX3fBb76g6uiE,14969
-lemonade/tools/server/serve.py,sha256=2Z3mbK-iVXAGA6jBDgJSwuWMbBRbmN_E0lMN2h-u6Wo,52230
+lemonade/tools/server/llamacpp.py,sha256=aDVjjkU2Z2PN25Uuy-lk6ByKPR8kg5r2X-YsVSs4vi8,15624
+lemonade/tools/server/serve.py,sha256=3_jBpi6THnnAmtKOxvPlOkIhSTTmrlZE3fr2Dpto-Q4,52794
 lemonade/tools/server/tool_calls.py,sha256=xrAlQwKG-nv2xLlf8f9CDSaUbyMn8ZtHkds9iZLG9K8,5230
 lemonade/tools/server/tray.py,sha256=SakwhZKPgo7VtWP4q10SaCcZdxKG95dnNsXdTu9Eei0,16030
 lemonade/tools/server/webapp.py,sha256=8Das5yXOaSBLZmSZ_eddJajQFxBhvl5D6GI_hHlGbE0,1040
@@ -57,14 +57,14 @@ lemonade/tools/server/utils/system_tray.py,sha256=b9lvNv9chJKQxvmH7qzAuUe6H9HsLu
 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-8.0.0.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-lemonade_sdk-8.0.0.dist-info/licenses/NOTICE.md,sha256=B8lEqi4QE41J9ljz4Riv2JgHD1v8GCZE6nNBHO3KIA0,2135
+lemonade_sdk-8.0.1.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+lemonade_sdk-8.0.1.dist-info/licenses/NOTICE.md,sha256=B8lEqi4QE41J9ljz4Riv2JgHD1v8GCZE6nNBHO3KIA0,2135
 lemonade_server/cli.py,sha256=fm1eORLKElHfzqO5VVicDmn9EbmqIffi1bynqacJeyw,11744
 lemonade_server/model_manager.py,sha256=HqbahDMRv1x8jyQj4pa1rXanlPmcCykt8tlI6WfaxjE,13023
 lemonade_server/pydantic_models.py,sha256=2ALw47C1VWGe2nKWjlEAzP1ggKYsky4xlahUFxQJCMs,2298
 lemonade_server/server_models.json,sha256=wTK_H9XDHLxqMWQJqbBsJwm50PhOR4gURyVj9Jm35PQ,6992
-lemonade_sdk-8.0.0.dist-info/METADATA,sha256=fJV_bzC7VCQjqpHTDkb8G58fvBlbsuqOa_zEJNZW5JU,7940
-lemonade_sdk-8.0.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-lemonade_sdk-8.0.0.dist-info/entry_points.txt,sha256=gJppn0ETtXXR6ceKWEIRdk42kMC7ps59EmU3NCPyPUk,144
-lemonade_sdk-8.0.0.dist-info/top_level.txt,sha256=10ap5GNiPhalO4V50LRoxA1FqRT9g3Xkia6BITu880k,42
-lemonade_sdk-8.0.0.dist-info/RECORD,,
+lemonade_sdk-8.0.1.dist-info/METADATA,sha256=s5q-KKS3Drrxxm1-wGLUP9c0HymN2RgC7PjMqr0biog,8225
+lemonade_sdk-8.0.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+lemonade_sdk-8.0.1.dist-info/entry_points.txt,sha256=gJppn0ETtXXR6ceKWEIRdk42kMC7ps59EmU3NCPyPUk,144
+lemonade_sdk-8.0.1.dist-info/top_level.txt,sha256=10ap5GNiPhalO4V50LRoxA1FqRT9g3Xkia6BITu880k,42
+lemonade_sdk-8.0.1.dist-info/RECORD,,