diff --git a/python/packages/autogen-agentchat/tests/test_assistant_agent.py b/python/packages/autogen-agentchat/tests/test_assistant_agent.py
index 6ad75f2ccae9..c087efe4ff60 100644
--- a/python/packages/autogen-agentchat/tests/test_assistant_agent.py
+++ b/python/packages/autogen-agentchat/tests/test_assistant_agent.py
@@ -66,6 +66,7 @@ async def test_run_with_tools(monkeypatch: pytest.MonkeyPatch) -> None:
                 usage=RequestUsage(prompt_tokens=10, completion_tokens=5),
                 thought="Calling pass function",
                 cached=False,
+                raw_response={"id": "mock-id", "provider": "replay"},
             ),
             "pass",
             "TERMINATE",
@@ -144,18 +145,21 @@ async def test_run_with_tools_and_reflection() -> None:
                 content=[FunctionCall(id="1", arguments=json.dumps({"input": "task"}), name="_pass_function")],
                 usage=RequestUsage(prompt_tokens=10, completion_tokens=5),
                 cached=False,
+                raw_response={"id": "mock-id", "provider": "replay"},
             ),
             CreateResult(
                 finish_reason="stop",
                 content="Hello",
                 usage=RequestUsage(prompt_tokens=10, completion_tokens=5),
                 cached=False,
+                raw_response={"id": "mock-id", "provider": "replay"},
             ),
             CreateResult(
                 finish_reason="stop",
                 content="TERMINATE",
                 usage=RequestUsage(prompt_tokens=10, completion_tokens=5),
                 cached=False,
+                raw_response={"id": "mock-id", "provider": "replay"},
             ),
         ],
         model_info={
@@ -246,6 +250,7 @@ async def test_run_with_parallel_tools() -> None:
                 usage=RequestUsage(prompt_tokens=10, completion_tokens=5),
                 thought="Calling pass and echo functions",
                 cached=False,
+                raw_response={"id": "mock-id", "provider": "replay"},
             ),
             "pass",
             "TERMINATE",
@@ -331,6 +336,7 @@ async def test_run_with_parallel_tools_with_empty_call_ids() -> None:
                 ],
                 usage=RequestUsage(prompt_tokens=10, completion_tokens=5),
                 cached=False,
+                raw_response={"id": "mock-id", "provider": "replay"},
             ),
             "pass",
             "TERMINATE",
@@ -672,6 +678,7 @@ async def test_handoffs() -> None:
                 ],
                 usage=RequestUsage(prompt_tokens=42, completion_tokens=43),
                 cached=False,
+                raw_response={"id": "mock-id", "provider": "replay"},
                 thought="Calling handoff function",
             )
         ],
@@ -1064,6 +1071,7 @@ async def test_list_chat_messages(monkeypatch: pytest.MonkeyPatch) -> None:
                 content="Response to message 1",
                 usage=RequestUsage(prompt_tokens=10, completion_tokens=5),
                 cached=False,
+                raw_response={"id": "mock-id", "provider": "replay"},
             )
         ]
     )
@@ -1269,6 +1277,7 @@ async def test_model_client_stream_with_tool_calls() -> None:
                 finish_reason="function_calls",
                 usage=RequestUsage(prompt_tokens=10, completion_tokens=5),
                 cached=False,
+                raw_response={"id": "mock-id", "provider": "replay"},
             ),
             "Example response 2 to task",
         ]
diff --git a/python/packages/autogen-agentchat/tests/test_code_executor_agent.py b/python/packages/autogen-agentchat/tests/test_code_executor_agent.py
index ddfc5d45c072..e971ab3bf1b7 100644
--- a/python/packages/autogen-agentchat/tests/test_code_executor_agent.py
+++ b/python/packages/autogen-agentchat/tests/test_code_executor_agent.py
@@ -142,11 +142,6 @@ async def test_self_debugging_loop() -> None:
 numbers = [10, 20, 30, 40, 50]
 mean = sum(numbers) / len(numbers
 print("The mean is:", mean)
-""".strip()
-    incorrect_code_result = """
-    mean = sum(numbers) / len(numbers
-                             ^
-SyntaxError: '(' was never closed
 """.strip()
     correct_code_block = """
 numbers = [10, 20, 30, 40, 50]
@@ -218,8 +213,8 @@ async def test_self_debugging_loop() -> None:
         elif isinstance(message, CodeExecutionEvent) and message_id == 1:
             # Step 2: First code execution
             assert (
-                incorrect_code_result in message.to_text().strip()
-            ), f"Expected {incorrect_code_result} in execution result, got: {message.to_text().strip()}"
+                "SyntaxError: '(' was never closed" in message.to_text()
+            ), f"Expected SyntaxError in execution result, got: {message.to_text().strip()}"
             incorrect_code_execution_event = message
 
         elif isinstance(message, CodeGenerationEvent) and message_id == 2:
diff --git a/python/packages/autogen-agentchat/tests/test_group_chat.py b/python/packages/autogen-agentchat/tests/test_group_chat.py
index 37763e866950..6a1a0c8b033d 100644
--- a/python/packages/autogen-agentchat/tests/test_group_chat.py
+++ b/python/packages/autogen-agentchat/tests/test_group_chat.py
@@ -450,6 +450,7 @@ async def test_round_robin_group_chat_with_tools(runtime: AgentRuntime | None) -
                 content=[FunctionCall(id="1", name="pass", arguments=json.dumps({"input": "pass"}))],
                 usage=RequestUsage(prompt_tokens=0, completion_tokens=0),
                 cached=False,
+                raw_response={"id": "mock-id", "provider": "replay"},
             ),
             "Hello",
             "TERMINATE",
@@ -1267,6 +1268,7 @@ async def test_swarm_handoff_using_tool_calls(runtime: AgentRuntime | None) -> N
                 content=[FunctionCall(id="1", name="handoff_to_agent2", arguments=json.dumps({}))],
                 usage=RequestUsage(prompt_tokens=0, completion_tokens=0),
                 cached=False,
+                raw_response={"id": "mock-id", "provider": "replay"},
             ),
             "Hello",
             "TERMINATE",
@@ -1367,6 +1369,7 @@ async def test_swarm_with_parallel_tool_calls(runtime: AgentRuntime | None) -> N
                 ],
                 usage=RequestUsage(prompt_tokens=0, completion_tokens=0),
                 cached=False,
+                raw_response={"id": "mock-id", "provider": "replay"},
             ),
             "Hello",
             "TERMINATE",
diff --git a/python/packages/autogen-core/src/autogen_core/models/_types.py b/python/packages/autogen-core/src/autogen_core/models/_types.py
index 6fd2e5c3534d..13489e04c5d4 100644
--- a/python/packages/autogen-core/src/autogen_core/models/_types.py
+++ b/python/packages/autogen-core/src/autogen_core/models/_types.py
@@ -1,5 +1,5 @@
 from dataclasses import dataclass
-from typing import List, Literal, Optional, Union
+from typing import Any, Dict, List, Literal, Optional, Union
 
 from pydantic import BaseModel, Field
 from typing_extensions import Annotated
@@ -125,3 +125,6 @@ class CreateResult(BaseModel):
     thought: Optional[str] = None
     """The reasoning text for the completion if available. Used for reasoning models
     and additional text content besides function calls."""
+
+    raw_response: Optional[Dict[str, Any]] = None
+    """Raw response from the model API, useful for custom field access."""
diff --git a/python/packages/autogen-core/tests/test_tool_agent.py b/python/packages/autogen-core/tests/test_tool_agent.py
index 727be91f6707..87deb9362214 100644
--- a/python/packages/autogen-core/tests/test_tool_agent.py
+++ b/python/packages/autogen-core/tests/test_tool_agent.py
@@ -113,6 +113,7 @@ async def create(
                     usage=RequestUsage(prompt_tokens=0, completion_tokens=0),
                     cached=False,
                     logprobs=None,
+                    raw_response={"id": "mock-id", "provider": "replay"},
                 )
             return CreateResult(
                 content="Done",
@@ -120,6 +121,7 @@ async def create(
                 usage=RequestUsage(prompt_tokens=0, completion_tokens=0),
                 cached=False,
                 logprobs=None,
+                raw_response={"id": "mock-id", "provider": "replay"},
             )
 
         def create_stream(
diff --git a/python/packages/autogen-ext/src/autogen_ext/experimental/task_centric_memory/utils/chat_completion_client_recorder.py b/python/packages/autogen-ext/src/autogen_ext/experimental/task_centric_memory/utils/chat_completion_client_recorder.py
index d9cb84a87c5d..8c3098a6c959 100644
--- a/python/packages/autogen-ext/src/autogen_ext/experimental/task_centric_memory/utils/chat_completion_client_recorder.py
+++ b/python/packages/autogen-ext/src/autogen_ext/experimental/task_centric_memory/utils/chat_completion_client_recorder.py
@@ -141,6 +141,7 @@ async def create(
                 finish_reason=data.get("finish_reason", "stop"),
                 usage=data.get("usage", RequestUsage(prompt_tokens=0, completion_tokens=0)),
                 cached=True,
+                raw_response=data.get("raw_response", {"id": "mock-id", "provider": "replay"}),
             )
             return result
 
diff --git a/python/packages/autogen-ext/src/autogen_ext/models/anthropic/_anthropic_client.py b/python/packages/autogen-ext/src/autogen_ext/models/anthropic/_anthropic_client.py
index 8fcec588fc68..6957bd656277 100644
--- a/python/packages/autogen-ext/src/autogen_ext/models/anthropic/_anthropic_client.py
+++ b/python/packages/autogen-ext/src/autogen_ext/models/anthropic/_anthropic_client.py
@@ -646,6 +646,7 @@ async def create(
             usage=usage,
             cached=False,
             thought=thought,
+            raw_response=result,
         )
 
         # Update usage statistics
@@ -863,6 +864,12 @@ async def create_stream(
             # Just text content
             content = "".join(text_content)
 
+        future: asyncio.Task[Message] = asyncio.ensure_future(
+            self._client.messages.create(**request_args)  # type: ignore
+        )
+
+        message_result: Message = cast(Message, await future)
+
         # Create the final result
         result = CreateResult(
             finish_reason=normalize_stop_reason(stop_reason),
@@ -870,6 +877,7 @@ async def create_stream(
             usage=usage,
             cached=False,
             thought=thought,
+            raw_response=message_result,
         )
 
         # Emit the end event.
diff --git a/python/packages/autogen-ext/src/autogen_ext/models/azure/_azure_ai_client.py b/python/packages/autogen-ext/src/autogen_ext/models/azure/_azure_ai_client.py
index 86cafce68661..14c1da89c90c 100644
--- a/python/packages/autogen-ext/src/autogen_ext/models/azure/_azure_ai_client.py
+++ b/python/packages/autogen-ext/src/autogen_ext/models/azure/_azure_ai_client.py
@@ -440,6 +440,7 @@ async def create(
             usage=usage,
             cached=False,
             thought=thought,
+            raw_response=result,
         )
 
         self.add_usage(usage)
diff --git a/python/packages/autogen-ext/src/autogen_ext/models/llama_cpp/_llama_cpp_completion_client.py b/python/packages/autogen-ext/src/autogen_ext/models/llama_cpp/_llama_cpp_completion_client.py
index 32df1b2f67ef..9772c42a6291 100644
--- a/python/packages/autogen-ext/src/autogen_ext/models/llama_cpp/_llama_cpp_completion_client.py
+++ b/python/packages/autogen-ext/src/autogen_ext/models/llama_cpp/_llama_cpp_completion_client.py
@@ -357,7 +357,11 @@ async def create(
         if not response_tool_calls and not response_text:
             logger.debug("DEBUG: No response text found. Returning empty response.")
             return CreateResult(
-                content="", usage=RequestUsage(prompt_tokens=0, completion_tokens=0), finish_reason="stop", cached=False
+                content="",
+                usage=RequestUsage(prompt_tokens=0, completion_tokens=0),
+                finish_reason="stop",
+                cached=False,
+                raw_response=response,
             )
 
         # Create a CreateResult object
@@ -373,6 +377,7 @@ async def create(
             usage=cast(RequestUsage, response["usage"]),
             finish_reason=normalize_stop_reason(finish_reason),  # type: ignore
             cached=False,
+            raw_response=response,
         )
 
         # If we are running in the context of a handler we can get the agent_id
diff --git a/python/packages/autogen-ext/src/autogen_ext/models/ollama/_ollama_client.py b/python/packages/autogen-ext/src/autogen_ext/models/ollama/_ollama_client.py
index 83699bbe548a..e58a01e64b3a 100644
--- a/python/packages/autogen-ext/src/autogen_ext/models/ollama/_ollama_client.py
+++ b/python/packages/autogen-ext/src/autogen_ext/models/ollama/_ollama_client.py
@@ -691,6 +691,7 @@ async def create(
             usage=usage,
             cached=False,
             logprobs=None,
+            raw_response=result,
             thought=thought,
         )
 
@@ -827,6 +828,7 @@ async def create_stream(
             usage=usage,
             cached=False,
             logprobs=None,
+            raw_response=None,
             thought=thought,
         )
 
diff --git a/python/packages/autogen-ext/src/autogen_ext/models/openai/_openai_client.py b/python/packages/autogen-ext/src/autogen_ext/models/openai/_openai_client.py
index ffe816e599c8..8e0c1b8c627a 100644
--- a/python/packages/autogen-ext/src/autogen_ext/models/openai/_openai_client.py
+++ b/python/packages/autogen-ext/src/autogen_ext/models/openai/_openai_client.py
@@ -722,6 +722,7 @@ async def create(
             cached=False,
             logprobs=logprobs,
             thought=thought,
+            raw_response=result,
         )
 
         self._total_usage = _add_usage(self._total_usage, usage)
@@ -956,6 +957,28 @@ async def create_stream(
             if isinstance(content, str) and self._model_info["family"] == ModelFamily.R1 and thought is None:
                 thought, content = parse_r1_content(content)
 
+        create_params = self._process_create_args(
+            messages,
+            tools,
+            json_output,
+            extra_create_args,
+        )
+
+        if create_params.response_format is not None:
+            result = await self._client.beta.chat.completions.parse(
+                messages=create_params.messages,
+                tools=(create_params.tools if len(create_params.tools) > 0 else NOT_GIVEN),
+                response_format=create_params.response_format,
+                **create_params.create_args,
+            )
+        else:
+            result = await self._client.chat.completions.create(
+                messages=create_params.messages,
+                stream=False,
+                tools=(create_params.tools if len(create_params.tools) > 0 else NOT_GIVEN),
+                **create_params.create_args,
+            )
+
         # Create the result.
         result = CreateResult(
             finish_reason=normalize_stop_reason(stop_reason),
@@ -964,6 +987,7 @@ async def create_stream(
             cached=False,
             logprobs=logprobs,
             thought=thought,
+            raw_response=result,
         )
 
         # Log the end of the stream.
diff --git a/python/packages/autogen-ext/src/autogen_ext/models/replay/_replay_chat_completion_client.py b/python/packages/autogen-ext/src/autogen_ext/models/replay/_replay_chat_completion_client.py
index 6e2b03beb2c7..55f6a9c02a3b 100644
--- a/python/packages/autogen-ext/src/autogen_ext/models/replay/_replay_chat_completion_client.py
+++ b/python/packages/autogen-ext/src/autogen_ext/models/replay/_replay_chat_completion_client.py
@@ -176,7 +176,11 @@ async def create(
             _, output_token_count = self._tokenize(response)
             self._cur_usage = RequestUsage(prompt_tokens=prompt_token_count, completion_tokens=output_token_count)
             response = CreateResult(
-                finish_reason="stop", content=response, usage=self._cur_usage, cached=self._cached_bool_value
+                finish_reason="stop",
+                content=response,
+                usage=self._cur_usage,
+                cached=self._cached_bool_value,
+                raw_response=response,
             )
         else:
             self._cur_usage = RequestUsage(
@@ -221,7 +225,11 @@ async def create_stream(
                 else:
                     yield token
             yield CreateResult(
-                finish_reason="stop", content=response, usage=self._cur_usage, cached=self._cached_bool_value
+                finish_reason="stop",
+                content=response,
+                usage=self._cur_usage,
+                cached=self._cached_bool_value,
+                raw_response=response,
             )
             self._update_total_usage()
         else:
diff --git a/python/packages/autogen-ext/src/autogen_ext/models/semantic_kernel/_sk_chat_completion_adapter.py b/python/packages/autogen-ext/src/autogen_ext/models/semantic_kernel/_sk_chat_completion_adapter.py
index 78f0aa5a24de..133cb69882d7 100644
--- a/python/packages/autogen-ext/src/autogen_ext/models/semantic_kernel/_sk_chat_completion_adapter.py
+++ b/python/packages/autogen-ext/src/autogen_ext/models/semantic_kernel/_sk_chat_completion_adapter.py
@@ -521,6 +521,7 @@ async def create(
             usage=RequestUsage(prompt_tokens=prompt_tokens, completion_tokens=completion_tokens),
             cached=False,
             thought=thought,
+            raw_response=result,
         )
 
     @staticmethod
@@ -676,6 +677,7 @@ async def create_stream(
                         finish_reason="function_calls",
                         usage=RequestUsage(prompt_tokens=prompt_tokens, completion_tokens=completion_tokens),
                         cached=False,
+                        raw_response=None,
                     )
                     return
 
@@ -698,6 +700,7 @@ async def create_stream(
             usage=RequestUsage(prompt_tokens=prompt_tokens, completion_tokens=completion_tokens),
             cached=False,
             thought=thought,
+            raw_response=None,
         )
 
         # Emit the end event.
diff --git a/python/packages/autogen-ext/tests/models/test_sk_chat_completion_adapter.py b/python/packages/autogen-ext/tests/models/test_sk_chat_completion_adapter.py
index 0f694b8492ac..41fecb67c9d8 100644
--- a/python/packages/autogen-ext/tests/models/test_sk_chat_completion_adapter.py
+++ b/python/packages/autogen-ext/tests/models/test_sk_chat_completion_adapter.py
@@ -211,7 +211,7 @@ async def mock_get_streaming_chat_message_contents(
                             created=1736674044,
                             model="gpt-4o-mini-2024-07-18",
                             object="chat.completion.chunk",
-                            service_tier="scale",
+                            service_tier="default",
                             system_fingerprint="fingerprint",
                             usage=CompletionUsage(prompt_tokens=20, completion_tokens=9, total_tokens=29),
                         ),
@@ -232,7 +232,7 @@ async def mock_get_streaming_chat_message_contents(
                             created=1736674044,
                             model="gpt-4o-mini-2024-07-18",
                             object="chat.completion.chunk",
-                            service_tier="scale",
+                            service_tier="default",
                             system_fingerprint="fingerprint",
                             usage=CompletionUsage(prompt_tokens=20, completion_tokens=9, total_tokens=29),
                         ),
@@ -253,7 +253,7 @@ async def mock_get_streaming_chat_message_contents(
                             created=1736674044,
                             model="gpt-4o-mini-2024-07-18",
                             object="chat.completion.chunk",
-                            service_tier="scale",
+                            service_tier="default",
                             system_fingerprint="fingerprint",
                             usage=CompletionUsage(prompt_tokens=20, completion_tokens=9, total_tokens=29),
                         ),
@@ -280,7 +280,7 @@ async def mock_get_streaming_chat_message_contents(
                             created=1736674044,
                             model="gpt-4o-mini-2024-07-18",
                             object="chat.completion.chunk",
-                            service_tier="scale",
+                            service_tier="default",
                             system_fingerprint="fingerprint",
                             usage=CompletionUsage(prompt_tokens=20, completion_tokens=9, total_tokens=29),
                         ),
@@ -503,7 +503,7 @@ async def mock_get_streaming_chat_message_contents(
                         created=1736674044,
                         model="r1",
                         object="chat.completion.chunk",
-                        service_tier="scale",
+                        service_tier="default",
                         system_fingerprint="fingerprint",
                         usage=CompletionUsage(prompt_tokens=20, completion_tokens=9, total_tokens=29),
                     ),
diff --git a/python/packages/autogen-ext/tests/test_openai_assistant_agent.py b/python/packages/autogen-ext/tests/test_openai_assistant_agent.py
index b76279c92a9f..bf5b1b980565 100644
--- a/python/packages/autogen-ext/tests/test_openai_assistant_agent.py
+++ b/python/packages/autogen-ext/tests/test_openai_assistant_agent.py
@@ -10,6 +10,7 @@
 import pytest
 from autogen_agentchat.messages import BaseChatMessage, TextMessage, ToolCallRequestEvent
 from autogen_core import CancellationToken
+from autogen_core.models import UserMessage
 from autogen_core.tools._base import BaseTool, Tool
 from autogen_ext.agents.openai import OpenAIAssistantAgent
 from azure.identity import DefaultAzureCredential, get_bearer_token_provider
@@ -17,6 +18,13 @@
 from pydantic import BaseModel
 
 
+def fake_to_model_message(self):
+    return UserMessage(content=self.content, source=self.source)
+
+
+TextMessage.to_model_message = fake_to_model_message
+
+
 class QuestionType(str, Enum):
     MULTIPLE_CHOICE = "MULTIPLE_CHOICE"
     FREE_RESPONSE = "FREE_RESPONSE"
diff --git a/python/session_1.json b/python/session_1.json
new file mode 100644
index 000000000000..8a072beb9928
--- /dev/null
+++ b/python/session_1.json
@@ -0,0 +1,24 @@
+[
+  {
+    "mode": "create",
+    "messages": [
+      {
+        "content": "Message 1",
+        "source": "User",
+        "type": "UserMessage"
+      }
+    ],
+    "response": {
+      "finish_reason": "stop",
+      "content": "Response to message 1",
+      "usage": {
+        "prompt_tokens": 2,
+        "completion_tokens": 4
+      },
+      "cached": true,
+      "logprobs": null,
+      "thought": null
+    },
+    "stream": []
+  }
+]
\ No newline at end of file
diff --git a/python/uv.lock b/python/uv.lock
index 0a8e566aee05..713cbded73a0 100644
--- a/python/uv.lock
+++ b/python/uv.lock
@@ -1,4 +1,5 @@
 version = 1
+revision = 1
 requires-python = ">=3.10, <3.13"
 resolution-markers = [
     "python_full_version >= '3.12.4' and sys_platform == 'darwin'",
@@ -90,7 +91,6 @@ wheels = [
 
 [[package]]
 name = "agbench"
-version = "0.0.1a1"
 source = { editable = "packages/agbench" }
 dependencies = [
     { name = "azure-identity" },
@@ -800,6 +800,7 @@ requires-dist = [
     { name = "unidiff", marker = "extra == 'canvas'", specifier = ">=0.7.5" },
     { name = "websockets", marker = "extra == 'docker-jupyter-executor'", specifier = ">=15.0.1" },
 ]
+provides-extras = ["anthropic", "langchain", "azure", "docker", "ollama", "openai", "file-surfer", "llama-cpp", "graphrag", "chromadb", "web-surfer", "magentic-one", "video-surfer", "diskcache", "redis", "grpc", "jupyter-executor", "docker-jupyter-executor", "task-centric-memory", "semantic-kernel-core", "gemini", "semantic-kernel-google", "semantic-kernel-hugging-face", "semantic-kernel-mistralai", "semantic-kernel-ollama", "semantic-kernel-onnx", "semantic-kernel-anthropic", "semantic-kernel-pandas", "semantic-kernel-aws", "semantic-kernel-dapr", "http-tool", "semantic-kernel-all", "rich", "mcp", "canvas"]
 
 [package.metadata.requires-dev]
 dev = [
@@ -829,7 +830,6 @@ requires-dist = [
 
 [[package]]
 name = "autogenstudio"
-version = "0.4.2"
 source = { editable = "packages/autogen-studio" }
 dependencies = [
     { name = "aiofiles" },
@@ -883,6 +883,7 @@ requires-dist = [
     { name = "uvicorn", marker = "extra == 'web'" },
     { name = "websockets" },
 ]
+provides-extras = ["web", "database"]
 
 [[package]]
 name = "autograd"
@@ -4729,7 +4730,6 @@ name = "nvidia-cublas-cu12"
 version = "12.4.5.8"
 source = { registry = "https://pypi.org/simple" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/7f/7f/7fbae15a3982dc9595e49ce0f19332423b260045d0a6afe93cdbe2f1f624/nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_aarch64.whl", hash = "sha256:0f8aa1706812e00b9f19dfe0cdb3999b092ccb8ca168c0db5b8ea712456fd9b3", size = 363333771 },
     { url = "https://files.pythonhosted.org/packages/ae/71/1c91302526c45ab494c23f61c7a84aa568b8c1f9d196efa5993957faf906/nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl", hash = "sha256:2fc8da60df463fdefa81e323eef2e36489e1c94335b5358bcb38360adf75ac9b", size = 363438805 },
 ]
 
@@ -4738,7 +4738,6 @@ name = "nvidia-cuda-cupti-cu12"
 version = "12.4.127"
 source = { registry = "https://pypi.org/simple" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/93/b5/9fb3d00386d3361b03874246190dfec7b206fd74e6e287b26a8fcb359d95/nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_aarch64.whl", hash = "sha256:79279b35cf6f91da114182a5ce1864997fd52294a87a16179ce275773799458a", size = 12354556 },
     { url = "https://files.pythonhosted.org/packages/67/42/f4f60238e8194a3106d06a058d494b18e006c10bb2b915655bd9f6ea4cb1/nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:9dec60f5ac126f7bb551c055072b69d85392b13311fcc1bcda2202d172df30fb", size = 13813957 },
 ]
 
@@ -4747,7 +4746,6 @@ name = "nvidia-cuda-nvrtc-cu12"
 version = "12.4.127"
 source = { registry = "https://pypi.org/simple" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/77/aa/083b01c427e963ad0b314040565ea396f914349914c298556484f799e61b/nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_aarch64.whl", hash = "sha256:0eedf14185e04b76aa05b1fea04133e59f465b6f960c0cbf4e37c3cb6b0ea198", size = 24133372 },
     { url = "https://files.pythonhosted.org/packages/2c/14/91ae57cd4db3f9ef7aa99f4019cfa8d54cb4caa7e00975df6467e9725a9f/nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:a178759ebb095827bd30ef56598ec182b85547f1508941a3d560eb7ea1fbf338", size = 24640306 },
 ]
 
@@ -4756,7 +4754,6 @@ name = "nvidia-cuda-runtime-cu12"
 version = "12.4.127"
 source = { registry = "https://pypi.org/simple" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/a1/aa/b656d755f474e2084971e9a297def515938d56b466ab39624012070cb773/nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_aarch64.whl", hash = "sha256:961fe0e2e716a2a1d967aab7caee97512f71767f852f67432d572e36cb3a11f3", size = 894177 },
     { url = "https://files.pythonhosted.org/packages/ea/27/1795d86fe88ef397885f2e580ac37628ed058a92ed2c39dc8eac3adf0619/nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:64403288fa2136ee8e467cdc9c9427e0434110899d07c779f25b5c068934faa5", size = 883737 },
 ]
 
@@ -4779,7 +4776,6 @@ dependencies = [
     { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
 ]
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/7a/8a/0e728f749baca3fbeffad762738276e5df60851958be7783af121a7221e7/nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_aarch64.whl", hash = "sha256:5dad8008fc7f92f5ddfa2101430917ce2ffacd86824914c82e28990ad7f00399", size = 211422548 },
     { url = "https://files.pythonhosted.org/packages/27/94/3266821f65b92b3138631e9c8e7fe1fb513804ac934485a8d05776e1dd43/nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl", hash = "sha256:f083fc24912aa410be21fa16d157fed2055dab1cc4b6934a0e03cba69eb242b9", size = 211459117 },
 ]
 
@@ -4788,7 +4784,6 @@ name = "nvidia-curand-cu12"
 version = "10.3.5.147"
 source = { registry = "https://pypi.org/simple" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/80/9c/a79180e4d70995fdf030c6946991d0171555c6edf95c265c6b2bf7011112/nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_aarch64.whl", hash = "sha256:1f173f09e3e3c76ab084aba0de819c49e56614feae5c12f69883f4ae9bb5fad9", size = 56314811 },
     { url = "https://files.pythonhosted.org/packages/8a/6d/44ad094874c6f1b9c654f8ed939590bdc408349f137f9b98a3a23ccec411/nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl", hash = "sha256:a88f583d4e0bb643c49743469964103aa59f7f708d862c3ddb0fc07f851e3b8b", size = 56305206 },
 ]
 
@@ -4802,7 +4797,6 @@ dependencies = [
     { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
 ]
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/46/6b/a5c33cf16af09166845345275c34ad2190944bcc6026797a39f8e0a282e0/nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_aarch64.whl", hash = "sha256:d338f155f174f90724bbde3758b7ac375a70ce8e706d70b018dd3375545fc84e", size = 127634111 },
     { url = "https://files.pythonhosted.org/packages/3a/e1/5b9089a4b2a4790dfdea8b3a006052cfecff58139d5a4e34cb1a51df8d6f/nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl", hash = "sha256:19e33fa442bcfd085b3086c4ebf7e8debc07cfe01e11513cc6d332fd918ac260", size = 127936057 },
 ]
 
@@ -4814,7 +4808,6 @@ dependencies = [
     { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
 ]
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/96/a9/c0d2f83a53d40a4a41be14cea6a0bf9e668ffcf8b004bd65633f433050c0/nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_aarch64.whl", hash = "sha256:9d32f62896231ebe0480efd8a7f702e143c98cfaa0e8a76df3386c1ba2b54df3", size = 207381987 },
     { url = "https://files.pythonhosted.org/packages/db/f7/97a9ea26ed4bbbfc2d470994b8b4f338ef663be97b8f677519ac195e113d/nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl", hash = "sha256:ea4f11a2904e2a8dc4b1833cc1b5181cde564edd0d5cd33e3c168eff2d1863f1", size = 207454763 },
 ]
 
@@ -4831,7 +4824,6 @@ name = "nvidia-nvjitlink-cu12"
 version = "12.4.127"
 source = { registry = "https://pypi.org/simple" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/02/45/239d52c05074898a80a900f49b1615d81c07fceadd5ad6c4f86a987c0bc4/nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_aarch64.whl", hash = "sha256:4abe7fef64914ccfa909bc2ba39739670ecc9e820c83ccc7a6ed414122599b83", size = 20552510 },
     { url = "https://files.pythonhosted.org/packages/ff/ff/847841bacfbefc97a00036e0fce5a0f086b640756dc38caea5e1bb002655/nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:06b3b9b25bf3f8af351d664978ca26a16d2c5127dbd53c0497e28d1fb9611d57", size = 21066810 },
 ]
 
@@ -4840,7 +4832,6 @@ name = "nvidia-nvtx-cu12"
 version = "12.4.127"
 source = { registry = "https://pypi.org/simple" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/06/39/471f581edbb7804b39e8063d92fc8305bdc7a80ae5c07dbe6ea5c50d14a5/nvidia_nvtx_cu12-12.4.127-py3-none-manylinux2014_aarch64.whl", hash = "sha256:7959ad635db13edf4fc65c06a6e9f9e55fc2f92596db928d169c0bb031e88ef3", size = 100417 },
     { url = "https://files.pythonhosted.org/packages/87/20/199b8713428322a2f22b722c62b8cc278cc53dffa9705d744484b5035ee9/nvidia_nvtx_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:781e950d9b9f60d8241ccea575b32f5105a5baf4c2351cab5256a24869f12a1a", size = 99144 },
 ]