chore: left over renaming (#67)

Co-authored-by: Harrison Saturley-Hall <454891+saturley-hall@users.noreply.github.com>
Co-authored-by: Harrison King Saturley-Hall <hsaturleyhal@nvidia.com>

examples/python_rs/llm/vllm/sdk_kv_router/README.md

@@ -21,7 +21,7 @@ Run this example using command below
 
 cd /workspace/examples/python_rs/llm/vllm
 
-dynemo-sdk serve sdk_kv_router.frontend:Frontend
+dynamo-sdk serve sdk_kv_router.frontend:Frontend
 ```
 
 
@@ -35,4 +35,4 @@ curl -X 'POST' \
   -d '{
   "msg": "In the heart of Eldoria, an ancient land of boundless magic and mysterious creatures, lies the long-forgotten city of Aeloria. Once a beacon of knowledge and power, Aeloria was buried beneath the shifting sands of time, lost to the world for centuries. You are an intrepid explorer, known for your unparalleled curiosity and courage, who has stumbled upon an ancient map hinting at ests that Aeloria holds a secret so profound that it has the potential to reshape the very fabric of reality. Your journey will take you through treacherous deserts, enchanted forests, and across perilous mountain ranges. Your Task: Character Background: Develop a detailed background for your character. Describe their motivations for seeking out Aeloria, their skills and weaknesses, and any personal connections to the ancient city or its legends. Are they driven by a quest for knowledge, a search for lost familt clue is hidden."
 }'
-````
+```
\ No newline at end of file

examples/python_rs/llm/vllm/sdk_kv_router/frontend.py

@@ -13,11 +13,12 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from dynemo.sdk import DYNEMO_IMAGE, api, depends, service
 from sdk_kv_router.processor import Processor
 
+from dynamo.sdk import DYNAMO_IMAGE, api, depends, service
 
-@service(traffic={"timeout": 10000}, image=DYNEMO_IMAGE)
+
+@service(traffic={"timeout": 10000}, image=DYNAMO_IMAGE)
 class Frontend:
     processor = depends(Processor)
 

examples/python_rs/llm/vllm/sdk_kv_router/processor.py

@@ -29,13 +29,13 @@ with bentoml.importing():
     from common.chat_processor import ChatProcessor, ProcessMixIn
     from common.protocol import MyRequestOutput, Tokens, vLLMGenerateRequest
 
-from dynemo.sdk import depends, dynemo_context, dynemo_endpoint, service
+from dynamo.sdk import depends, dynamo_context, dynamo_endpoint, service
 
 
 @service(
-    dynemo={
+    dynamo={
         "enabled": True,
-        "namespace": "dynemo",
+        "namespace": "dynamo",
     },
     resources={"cpu": "10", "memory": "20Gi"},
     workers=1,
@@ -92,7 +92,7 @@ class Processor(ProcessMixIn):
                 metrics=output.metrics,
             )
 
-    @dynemo_endpoint()
+    @dynamo_endpoint()
     async def generate(self, raw_request: ChatCompletionRequest):
         request_id = str(uuid.uuid4())
         (
@@ -108,8 +108,8 @@ class Processor(ProcessMixIn):
         ):
             worker_id = worker
             break
-        runtime = dynemo_context["runtime"]
-        comp_ns, comp_name = VllmEngine.dynemo_address()  # type: ignore
+        runtime = dynamo_context["runtime"]
+        comp_ns, comp_name = VllmEngine.dynamo_address()  # type: ignore
         worker_client = (
             await runtime.namespace(comp_ns)
             .component(comp_name)

examples/python_rs/llm/vllm/sdk_kv_router/router.py

@@ -17,10 +17,11 @@ from enum import Enum
 
 import bentoml
 from common.protocol import Tokens
-from dynemo.sdk import async_onstart, dynemo_context, dynemo_endpoint, service
+
+from dynamo.sdk import async_onstart, dynamo_context, dynamo_endpoint, service
 
 with bentoml.importing():
-    from dynemo.runtime import KvRouter
+    from dynamo.runtime import KvRouter
 
 
 WorkerId = str
@@ -33,9 +34,9 @@ class RoutingStrategy(Enum):
 
 
 @service(
-    dynemo={
+    dynamo={
         "enabled": True,
-        "namespace": "dynemo",
+        "namespace": "dynamo",
     },
     resources={"cpu": "10", "memory": "20Gi"},
     workers=1,
@@ -48,13 +49,13 @@ class Router:
     def __init__(self):
         self.model_name = "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"
         self.routing_strategy = RoutingStrategy.PREFIX
-        self.runtime = dynemo_context["runtime"]
+        self.runtime = dynamo_context["runtime"]
         self.min_workers = 1
 
     @async_onstart
     async def init_engine(self):
         workers_client = (
-            await self.runtime.namespace("dynemo")
+            await self.runtime.namespace("dynamo")
             .component("VllmEngine")
             .endpoint("generate")
             .client()
@@ -74,11 +75,11 @@ class Router:
             )
             await asyncio.sleep(5)
 
-        kv_listener = self.runtime.namespace("dynemo").component(self.model_name)
+        kv_listener = self.runtime.namespace("dynamo").component(self.model_name)
         await kv_listener.create_service()
         self.router = KvRouter(self.runtime, kv_listener)
 
-    @dynemo_endpoint()
+    @dynamo_endpoint()
     async def generate(self, request: Tokens):
         lora_id = 0
         worker_id = ""

examples/python_rs/llm/vllm/sdk_kv_router/worker.py

@@ -27,11 +27,11 @@ with bentoml.importing():
     from common.protocol import MyRequestOutput, vLLMGenerateRequest
     from vllm.engine.multiprocessing.client import MQLLMEngineClient
 
-from dynemo.llm import KvMetricsPublisher
-from dynemo.sdk import (
+from dynamo.llm import KvMetricsPublisher
+from dynamo.sdk import (
     async_onstart,
-    dynemo_context,
-    dynemo_endpoint,
+    dynamo_context,
+    dynamo_endpoint,
     server_context,
     service,
 )
@@ -42,9 +42,9 @@ lease_id = None
 
 
 @service(
-    dynemo={
+    dynamo={
         "enabled": True,
-        "namespace": "dynemo",
+        "namespace": "dynamo",
     },
     resources={"gpu": 1, "cpu": "10", "memory": "20Gi"},
     workers=1,
@@ -63,9 +63,9 @@ class VllmEngine(BaseVllmEngine):
             block_size=64,
             max_model_len=16384,
         )
-        VLLM_WORKER_ID = dynemo_context["endpoints"][0].lease_id()
+        VLLM_WORKER_ID = dynamo_context["endpoints"][0].lease_id()
         os.environ["VLLM_WORKER_ID"] = str(VLLM_WORKER_ID)
-        os.environ["VLLM_KV_NAMESPACE"] = "dynemo"
+        os.environ["VLLM_KV_NAMESPACE"] = "dynamo"
         os.environ["VLLM_KV_COMPONENT"] = "vllm"
         vllm_logger.info(f"Generate endpoint ID: {VLLM_WORKER_ID}")
         os.environ["CUDA_VISIBLE_DEVICES"] = f"{server_context.worker_index - 1}"
@@ -74,7 +74,7 @@ class VllmEngine(BaseVllmEngine):
         super().__init__(self.engine_args)
 
     async def create_metrics_publisher_endpoint(self):
-        component = dynemo_context["component"]
+        component = dynamo_context["component"]
         await self.metrics_publisher.create_endpoint(component)
 
     @async_onstart
@@ -88,7 +88,7 @@ class VllmEngine(BaseVllmEngine):
         task = asyncio.create_task(self.create_metrics_publisher_endpoint())
         task.add_done_callback(lambda _: print("metrics publisher endpoint created"))
 
-    @dynemo_endpoint()
+    @dynamo_endpoint()
     async def generate(self, request: vLLMGenerateRequest):
         sampling_params = request.sampling_params
         # rust HTTP requires Delta streaming

examples/rust/Cargo.toml

@@ -27,8 +27,8 @@ version = "0.2.0"
 edition = "2021"
 authors = ["NVIDIA"]
 license = "Apache-2.0"
-homepage = "https://github.com/dynemo-ai/dynemo"
-repository = "https://github.com/dynemo-ai/dynemo.git"
+homepage = "https://github.com/ai-dynamo/dynamo"
+repository = "https://github.com/ai-dynamo/dynamo.git"
 
 
 [workspace.dependencies]

examples/rust/service_metrics/README.md

@@ -27,7 +27,7 @@ Annotated { data: Some("o"), id: None, event: None, comment: None }
 Annotated { data: Some("r"), id: None, event: None, comment: None }
 Annotated { data: Some("l"), id: None, event: None, comment: None }
 Annotated { data: Some("d"), id: None, event: None, comment: None }
-ServiceSet { services: [ServiceInfo { name: "dynemo_init_backend_720278f8", id: "eOHMc4ndRw8s5flv4WOZx7", version: "0.0.1", started: "2025-02-26T18:54:04.917294605Z", endpoints: [EndpointInfo { name: "dynemo_init_backend_720278f8-generate-694d951a80e06abf", subject: "dynemo_init_backend_720278f8.generate-694d951a80e06abf", data: Some(Metrics(Object {"average_processing_time": Number(53662), "data": Object {"val": Number(10)}, "last_error": String(""), "num_errors": Number(0), "num_requests": Number(2), "processing_time": Number(107325), "queue_group": String("q")})) }] }] }
+ServiceSet { services: [ServiceInfo { name: "dynamo_init_backend_720278f8", id: "eOHMc4ndRw8s5flv4WOZx7", version: "0.0.1", started: "2025-02-26T18:54:04.917294605Z", endpoints: [EndpointInfo { name: "dynamo_init_backend_720278f8-generate-694d951a80e06abf", subject: "dynamo_init_backend_720278f8.generate-694d951a80e06abf", data: Some(Metrics(Object {"average_processing_time": Number(53662), "data": Object {"val": Number(10)}, "last_error": String(""), "num_errors": Number(0), "num_requests": Number(2), "processing_time": Number(107325), "queue_group": String("q")})) }] }] }
 ```
 
 Note the following stats in the output demonstrate the custom

launch/dynamo-run/Cargo.toml

@@ -18,7 +18,7 @@ name = "dynamo-run"
 version = "0.1.0"
 edition = "2021"
 authors = ["NVIDIA"]
-homepage = "https://github.com/dynemo-ai/dynemo"
+homepage = "https://github.com/ai-dynamo/dynamo"
 license = "Apache-2.0"
 
 [features]

lib/bindings/c/Cargo.toml

@@ -19,8 +19,8 @@ version = "0.2.1"
 edition = "2021"
 authors = ["NVIDIA"]
 license = "Apache-2.0"
-homepage = "https://github.com/dynemo-ai/dynemo"
-repository = "https://github.com/dynemo-ai/dynemo.git"
+homepage = "https://github.com/ai-dynamo/dynamo"
+repository = "https://github.com/ai-dynamo/dynamo.git"
 
 [lib]
 name = "dynamo_llm_capi"

lib/bindings/c/cbindgen.toml

@@ -15,7 +15,7 @@
 
 language = "C++"
 cpp_compat = true
-include_guard = "__NVIDIA_DYNEMO_LLM_API__"
+include_guard = "__NVIDIA_DYNAMO_LLM_API__"
 
 
 [enum]

lib/bindings/python/Cargo.toml

@@ -19,8 +19,8 @@ version = "0.2.1"
 edition = "2021"
 authors = ["NVIDIA"]
 license = "Apache-2.0"
-homepage = "https://github.com/dynemo-ai/dynemo"
-repository = "https://github.com/dynemo-ai/dynemo.git"
+homepage = "https://github.com/ai-dynamo/dynamo"
+repository = "https://github.com/ai-dynamo/dynamo.git"
 
 [lib]
 path = "rust/lib.rs"

lib/llm/Cargo.toml

@@ -18,8 +18,8 @@ version = "0.2.1"
 edition = "2021"
 authors = ["NVIDIA"]
 license = "Apache-2.0"
-homepage = "https://github.com/dynemo-ai/dynemo"
-repository = "https://github.com/dynemo-ai/dynemo.git"
+homepage = "https://github.com/ai-dynamo/dynamo"
+repository = "https://github.com/ai-dynamo/dynamo.git"
 
 [package]
 name = "dynamo-llm"

lib/runtime/Cargo.toml

@@ -21,8 +21,8 @@ version = "0.2.1" # TODO: Centralize Version Automation
 edition = "2021"
 authors = ["NVIDIA"]
 license = "Apache-2.0"
-homepage = "https://github.com/dynemo-ai/dynemo"
-repository = "https://github.com/dynemo-ai/dynemo.git"
+homepage = "https://github.com/ai-dynamo/dynamo"
+repository = "https://github.com/ai-dynamo/dynamo.git"
 keywords = ["llm", "genai", "inference", "nvidia", "distributed", "dynamo"]
 
 [features]

pyproject.toml

@@ -19,7 +19,7 @@ version = "0.2.1"
 description = "Distributed Inference Framework"
 readme = "README.md"
 authors = [
-    { name = "NVIDIA Inc.", email = "sw-dl-dynemo@nvidia.com" },
+    { name = "NVIDIA Inc.", email = "sw-dl-dynamo@nvidia.com" },
 ]
 license = { file = "LICENSE" }
 requires-python = ">=3.10"
@@ -146,4 +146,4 @@ ignore_missing_imports = true
 
 # declare namespace packages
 [tool.setuptools]
-namespace-packages = ["dynemo", "dynemo.sdk"]
+namespace-packages = ["dynamo", "dynamo.sdk"]