chore: rename dynamo (#44)

Co-authored-by: Biswa Panda <biswa.panda@gmail.com>

.dockerignore

@@ -19,7 +19,7 @@
 **/*.plan
 **/.cache/*
 **/*onnx*
-# Engine must be allowed because code contains dynemo_engine.py
+# Engine must be allowed because code contains dynamo_engine.py
 **/*tensorrtllm_engines*
 **/*tensorrtllm_models*
 **/*tensorrtllm_checkpoints*

.github/workflows/pre-merge-rust.yml

@@ -40,7 +40,7 @@ jobs:
   pre-merge-rust:
     runs-on: ubuntu-latest
     strategy:
-      matrix: { dir: ['lib/runtime', 'lib/llm', 'lib/bindings/c', 'lib/bindings/python', 'launch/dynemo-run', 'components/metrics', 'examples/rust'] }
+      matrix: { dir: ['lib/runtime', 'lib/llm', 'lib/bindings/c', 'lib/bindings/python', 'launch/dynamo-run', 'components/metrics', 'examples/rust'] }
     permissions:
       contents: read
     steps:

ATTRIBUTIONS.md

@@ -17,7 +17,7 @@ limitations under the License.
 
 # Open Source License Attribution
 
-   Dynemo uses Open Source components. You can find the details of these open-source projects along with license information below.
+   Dynamo uses Open Source components. You can find the details of these open-source projects along with license information below.
    We are grateful to the developers for their contributions to open source and acknowledge these below.
 
 ## nats-py - [Apache License 2.0](https://github.com/nats-io/nats.py/blob/main/LICENSE)

CODEOWNERS

-# CODEOWNERS file for Dynemo
+# CODEOWNERS file for Dynamo
 #
 # For more information about CODEOWNERS files, see:
 # https://docs.github.com/en/repositories/managing-your-repositorys-settings-and-features/customizing-your-repository/about-code-owners

README.md

@@ -15,17 +15,17 @@ See the License for the specific language governing permissions and
 limitations under the License.
 -->
 
-# Dynemo
+# Dynamo
 
 <h4> A Datacenter Scale Distributed Inference Serving Framework </h4>
 
 [![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
-[![GitHub Release](https://img.shields.io/github/v/release/dynemo-ai/dynemo)](https://github.com/dynemo-ai/dynemo/releases/latest)
+[![GitHub Release](https://img.shields.io/github/v/release/dynemo-ai/dynamo)](https://github.com/dynemo-ai/dynemo/releases/latest)
 
 
-Dynemo is a flexible, component based, data center scale
+Dynamo is a flexible, component based, data center scale
 inference serving framework designed to leverage the strengths of the
-standalone Dynemo Inference Server while expanding its capabilities
+standalone Dynamo Inference Server while expanding its capabilities
 to meet the demands of complex use cases including those of Generative
 AI. It is designed to enable developers to implement and customize
 routing, load balancing, scaling and workflow definitions at the data
@@ -36,17 +36,17 @@ center scale without sacrificing performance or ease of use.
 > rapid-prototyping stage and we are actively looking for feedback and
 > collaborators.
 
-## Building Dynemo
+## Building Dynamo
 
 ### Requirements
-Dynemo development and examples are container based.
+Dynamo development and examples are container based.
 
 * [Docker](https://docs.docker.com/get-started/get-docker/)
 * [buildx](https://github.com/docker/buildx)
 
 ### Development
 
-You can build the Dynemo container using the build scripts
+You can build the Dynamo container using the build scripts
 in `container/` (or directly with `docker build`).
 
 We provide 3 types of builds:
@@ -62,9 +62,9 @@ For example, if you want to build a container for the `STANDARD` backends you ca
 
 Please see the instructions in the corresponding example for specific build instructions.
 
-## Running Dynemo for Local Testing and Development
+## Running Dynamo for Local Testing and Development
 
-You can run the Dynemo container using the run scripts in
+You can run the Dynamo container using the run scripts in
 `container/` (or directly with `docker run`).
 
 The run script offers a few common workflows:
@@ -72,7 +72,7 @@ The run script offers a few common workflows:
 1. Running a command in a container and exiting.
 
 ```
-./container/run.sh -- python3 -c "import dynemo.runtime; help(dynemo.runtime)"
+./container/run.sh -- python3 -c "import dynamo.runtime; help(dynamo.runtime)"
 ```
 
 2. Starting an interactive shell.
@@ -95,7 +95,7 @@ deployment instructions.
 
 ## Rust Based Runtime
 
-Dynemo has a new rust based distributed runtime with
+Dynamo has a new rust based distributed runtime with
 implementation under development. The rust based runtime enables
 serving arbitrary python code as well as native rust. Please note the
 APIs are subject to change.
@@ -114,7 +114,7 @@ bindings.
 An intermediate example expanding further on the concepts introduced
 in the Hello World example. In this example, we demonstrate
 [Disaggregated Serving](https://arxiv.org/abs/2401.09670) as an
-application of the components defined in Dynemo.
+application of the components defined in Dynamo.
 
 # Disclaimers
 

codespell.txt

-dynamo->dynemo
-dynmo->dynemo
+dynmo->dynamo

components/metrics/Cargo.lock

@@ -1005,7 +1005,7 @@ dependencies = [
 ]
 
 [[package]]
-name = "dynemo-llm"
+name = "dynamo-llm"
 version = "0.2.1"
 dependencies = [
  "anyhow",
@@ -1020,7 +1020,7 @@ dependencies = [
  "chrono",
  "cmake",
  "derive_builder",
- "dynemo-runtime",
+ "dynamo-runtime",
  "either",
  "erased-serde",
  "futures",
@@ -1054,7 +1054,7 @@ dependencies = [
 ]
 
 [[package]]
-name = "dynemo-runtime"
+name = "dynamo-runtime"
 version = "0.2.1"
 dependencies = [
  "anyhow",
@@ -2202,8 +2202,8 @@ dependencies = [
  "async-nats",
  "axum 0.6.20",
  "clap",
- "dynemo-llm",
- "dynemo-runtime",
+ "dynamo-llm",
+ "dynamo-runtime",
  "futures",
  "opentelemetry",
  "opentelemetry-prometheus",

components/metrics/Cargo.toml

@@ -22,8 +22,8 @@ license = "Apache-2.0"
 [dependencies]
 # local
 
-dynemo-runtime = { path = "../../lib/runtime" }
-dynemo-llm = { path = "../../lib/llm" }
+dynamo-runtime = { path = "../../lib/runtime" }
+dynamo-llm = { path = "../../lib/llm" }
 
 # workspace - todo
 

components/metrics/README.md

@@ -12,16 +12,16 @@ This will:
 For example:
 ```bash
 # For more details, try DYN_LOG=debug
-DYN_LOG=info cargo run --bin metrics -- --namespace dynemo --component backend --endpoint generate
+DYN_LOG=info cargo run --bin metrics -- --namespace dynamo --component backend --endpoint generate
 
-# 2025-02-26T18:45:05.467026Z  INFO metrics: Creating unique instance of Metrics at dynemo/components/metrics/instance
-# 2025-02-26T18:45:05.472146Z  INFO metrics: Scraping service dynemo_backend_720278f8 and filtering on subject dynemo_backend_720278f8.generate
+# 2025-02-26T18:45:05.467026Z  INFO metrics: Creating unique instance of Metrics at dynamo/components/metrics/instance
+# 2025-02-26T18:45:05.472146Z  INFO metrics: Scraping service dynamo_backend_720278f8 and filtering on subject dynamo_backend_720278f8.generate
 # ...
 ```
 
 With no matching endpoints running to collect stats from, you should see warnings in the logs:
 ```bash
-2025-02-26T18:45:06.474161Z  WARN metrics: No endpoints found matching subject dynemo_backend_720278f8.generate
+2025-02-26T18:45:06.474161Z  WARN metrics: No endpoints found matching subject dynamo_backend_720278f8.generate
 ```
 
 After a matching endpoint gets started, you should see the warnings stop
@@ -30,7 +30,7 @@ when the endpoint gets automatically discovered.
 When stats are found from target endpoints, the metrics component will
 aggregate them and publish them to a prometheus server running on `localhost:9091/metrics` by default:
 ```
-2025-02-28T04:05:58.077901Z  INFO metrics: Aggregated metrics: ProcessedEndpoints { endpoints: [Endpoint { name: "worker-7587884888253033398", subject: "dynemo_backend_720278f8.generate-694d951a80e06bb6", data: ForwardPassMetrics { request_active_slots: 58, request_total_slots: 100, kv_active_blocks: 77, kv_total_blocks: 100 } }, Endpoint { name: "worker-7587884888253033401", subject: "dynemo_backend_720278f8.generate-694d951a80e06bb9", data: ForwardPassMetrics { request_active_slots: 71, request_total_slots: 100, kv_active_blocks: 29, kv_total_blocks: 100 } }], worker_ids: [7587884888253033398, 7587884888253033401], load_avg: 53.0, load_std: 24.0 }
+2025-02-28T04:05:58.077901Z  INFO metrics: Aggregated metrics: ProcessedEndpoints { endpoints: [Endpoint { name: "worker-7587884888253033398", subject: "dynamo_backend_720278f8.generate-694d951a80e06bb6", data: ForwardPassMetrics { request_active_slots: 58, request_total_slots: 100, kv_active_blocks: 77, kv_total_blocks: 100 } }, Endpoint { name: "worker-7587884888253033401", subject: "dynamo_backend_720278f8.generate-694d951a80e06bb9", data: ForwardPassMetrics { request_active_slots: 71, request_total_slots: 100, kv_active_blocks: 29, kv_total_blocks: 100 } }], worker_ids: [7587884888253033398, 7587884888253033401], load_avg: 53.0, load_std: 24.0 }
 ```
 
 To see the metrics being published in prometheus format, you can run:

components/metrics/src/bin/mock_worker.rs

@@ -14,10 +14,10 @@
 // limitations under the License.
 
 use async_nats::service::endpoint::Stats;
-use dynemo_llm::kv_router::{
+use dynamo_llm::kv_router::{
     protocols::ForwardPassMetrics, scheduler::KVHitRateEvent, KV_HIT_RATE_SUBJECT,
 };
-use dynemo_runtime::{
+use dynamo_runtime::{
     component::Namespace,
     logging,
     pipeline::{
@@ -123,7 +123,7 @@ fn mock_stats_handler(_stats: Stats) -> serde_json::Value {
 }
 
 async fn backend(runtime: DistributedRuntime) -> Result<()> {
-    let namespace = runtime.namespace("dynemo")?;
+    let namespace = runtime.namespace("dynamo")?;
 
     // Spawn background task for publishing KV hit rate events
     let namespace_clone = namespace.clone();

components/metrics/src/lib.rs

@@ -20,11 +20,11 @@ use prometheus::{register_counter_vec, register_gauge_vec};
 use serde::{Deserialize, Serialize};
 use std::net::SocketAddr;
 
-use dynemo_llm::kv_router::protocols::ForwardPassMetrics;
-use dynemo_llm::kv_router::scheduler::Endpoint;
-use dynemo_llm::kv_router::scoring::ProcessedEndpoints;
+use dynamo_llm::kv_router::protocols::ForwardPassMetrics;
+use dynamo_llm::kv_router::scheduler::Endpoint;
+use dynamo_llm::kv_router::scoring::ProcessedEndpoints;
 
-use dynemo_runtime::{distributed::Component, service::EndpointInfo, utils::Duration, Result};
+use dynamo_runtime::{distributed::Component, service::EndpointInfo, utils::Duration, Result};
 
 /// Configuration for LLM worker load capacity metrics
 #[derive(Debug, Clone, Serialize, Deserialize)]

components/metrics/src/main.rs

@@ -27,9 +27,9 @@
 //!   - ISL Blocks: Cumulative count of total blocks in all KV hit rate events
 //!   - Overlap Blocks: Cumulative count of blocks that were already in the KV cache
 use clap::Parser;
-use dynemo_llm::kv_router::scheduler::KVHitRateEvent;
-use dynemo_llm::kv_router::KV_HIT_RATE_SUBJECT;
-use dynemo_runtime::{
+use dynamo_llm::kv_router::scheduler::KVHitRateEvent;
+use dynamo_llm::kv_router::KV_HIT_RATE_SUBJECT;
+use dynamo_runtime::{
     error, logging,
     traits::events::{EventPublisher, EventSubscriber},
     utils::{Duration, Instant},
@@ -57,7 +57,7 @@ struct Args {
     endpoint: String,
 
     /// Namespace to operate in
-    #[arg(long, env = "DYN_NAMESPACE", default_value = "dynemo")]
+    #[arg(long, env = "DYN_NAMESPACE", default_value = "dynamo")]
     namespace: String,
 
     /// Polling interval in seconds (minimum 1 second)

container/Dockerfile

@@ -16,7 +16,7 @@
 ARG BASE_IMAGE="nvcr.io/nvidia/tritonserver"
 ARG BASE_IMAGE_TAG="25.01-py3"
 
-FROM ${BASE_IMAGE}:${BASE_IMAGE_TAG} AS dynemo
+FROM ${BASE_IMAGE}:${BASE_IMAGE_TAG} AS dynamo
 
 # TODO: non root user by default
 
@@ -34,7 +34,7 @@ RUN rustup toolchain install 1.85.0-x86_64-unknown-linux-gnu
 
 # Install OpenAI-compatible frontend and its dependencies from triton server
 # repository. These are used to have a consistent interface, schema, and FastAPI
-# app between Triton Core and Dynemo implementations.
+# app between Triton Core and Dynamo implementations.
 ARG OPENAI_SERVER_TAG="r25.01"
 RUN mkdir -p /opt/tritonserver/python && \
     cd /opt/tritonserver/python && \
@@ -78,7 +78,7 @@ ARG TENSORRTLLM_SKIP_CLONE=
 ENV FRAMEWORK=${FRAMEWORK}
 RUN --mount=type=bind,source=./container/deps/requirements.tensorrtllm.txt,target=/tmp/requirements.txt \
     --mount=type=bind,source=./container/deps/clone_tensorrtllm.sh,target=/tmp/clone_tensorrtllm.sh \
-    if [[ "$FRAMEWORK" == "TENSORRTLLM" ]] ; then pip install --timeout=2000 -r /tmp/requirements.txt; if [ ${TENSORRTLLM_SKIP_CLONE} -ne 1 ] ; then /tmp/clone_tensorrtllm.sh --tensorrtllm-backend-repo-tag ${TENSORRTLLM_BACKEND_REPO_TAG} --tensorrtllm-backend-rebuild ${TENSORRTLLM_BACKEND_REBUILD} --dynemo-llm-path /opt/dynemo/llm_binding ; fi ; fi
+    if [[ "$FRAMEWORK" == "TENSORRTLLM" ]] ; then pip install --timeout=2000 -r /tmp/requirements.txt; if [ ${TENSORRTLLM_SKIP_CLONE} -ne 1 ] ; then /tmp/clone_tensorrtllm.sh --tensorrtllm-backend-repo-tag ${TENSORRTLLM_BACKEND_REPO_TAG} --tensorrtllm-backend-rebuild ${TENSORRTLLM_BACKEND_REBUILD} --dynamo-llm-path /opt/dynamo/llm_binding ; fi ; fi
 
 
 RUN --mount=type=bind,source=./container/deps/requirements.standard.txt,target=/tmp/requirements.txt \
@@ -106,7 +106,7 @@ ENV VLLM_GENERATE_WORKERS=${VLLM_FRAMEWORK:+1}
 ENV VLLM_BASELINE_TP_SIZE=${VLLM_FRAMEWORK:+1}
 ENV VLLM_CONTEXT_TP_SIZE=${VLLM_FRAMEWORK:+1}
 ENV VLLM_GENERATE_TP_SIZE=${VLLM_FRAMEWORK:+1}
-ENV VLLM_KV_CAPI_PATH="/opt/dynemo/bindings/lib/libdynemo_llm_capi.so"
+ENV VLLM_KV_CAPI_PATH="/opt/dynamo/bindings/lib/libdynamo_llm_capi.so"
 ENV PYTHONUNBUFFERED=1
 
 # Install NATS - pointing toward NATS github instead of binaries.nats.dev due to server instability
@@ -154,7 +154,7 @@ RUN cd examples/rust && \
     cp target/release/http /usr/local/bin/ && \
     cp target/release/llmctl /usr/local/bin/
 
-COPY deploy/dynemo/sdk /workspace/deploy/dynemo/sdk
+COPY deploy/dynamo/sdk /workspace/deploy/dynamo/sdk
 
 
 # Generate C bindings. Note that this is required for TRTLLM backend re-build
@@ -162,30 +162,30 @@ COPY lib/bindings /workspace/lib/bindings
 RUN cd lib/bindings/c/ && \
     cargo build --release --locked && cargo doc --no-deps
 
-# Install uv, create virtualenv for general use, and build dynemo wheel
+# Install uv, create virtualenv for general use, and build dynamo wheel
 COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /bin/
-RUN mkdir /opt/dynemo && \
-    uv venv /opt/dynemo/venv --python 3.12 && \
-    source /opt/dynemo/venv/bin/activate && \
+RUN mkdir /opt/dynamo && \
+    uv venv /opt/dynamo/venv --python 3.12 && \
+    source /opt/dynamo/venv/bin/activate && \
     uv build --wheel --out-dir /workspace/dist && \
-    uv pip install /workspace/dist/dynemo*cp312*.whl && \
-    cd /workspace/deploy/dynemo/sdk && \
+    uv pip install /workspace/dist/dynamo*cp312*.whl && \
+    cd /workspace/deploy/dynamo/sdk && \
     uv build --wheel --out-dir /workspace/dist && \
-    uv pip install /workspace/dist/dynemo_sdk*any.whl
+    uv pip install /workspace/dist/dynamo_sdk*any.whl
 
 # Package the bindings
-RUN mkdir -p /opt/dynemo/bindings/wheels && \
-    mkdir /opt/dynemo/bindings/lib && \
-    cp dist/dynemo*cp312*.whl /opt/dynemo/bindings/wheels/. && \
-    cp lib/bindings/c/target/release/libdynemo_llm_capi.so /opt/dynemo/bindings/lib/. && \
-    cp -r lib/bindings/c/include /opt/dynemo/bindings/.
+RUN mkdir -p /opt/dynamo/bindings/wheels && \
+    mkdir /opt/dynamo/bindings/lib && \
+    cp dist/dynamo*cp312*.whl /opt/dynamo/bindings/wheels/. && \
+    cp lib/bindings/c/target/release/libdynamo_llm_capi.so /opt/dynamo/bindings/lib/. && \
+    cp -r lib/bindings/c/include /opt/dynamo/bindings/.
 
-# Install dynemo.runtime and dynemo.llm wheels globally in container for tests that
+# Install dynamo.runtime and dynamo.llm wheels globally in container for tests that
 # currently run without virtual environment activated.
 # TODO: In future, we may use a virtualenv for everything and remove this.
-RUN cd /opt/dynemo/bindings/wheels && \
-    pip install dynemo*cp312*.whl  && \
-    pip install /workspace/dist/dynemo_sdk*any.whl
+RUN cd /opt/dynamo/bindings/wheels && \
+    pip install dynamo*cp312*.whl  && \
+    pip install /workspace/dist/dynamo_sdk*any.whl
 
 # Copy everything in after ginstall steps to avoid re-running build/install
 # commands on unrelated changes in other dirs.

container/Dockerfile.vllm

@@ -24,17 +24,17 @@ ENV PATH=/usr/local/bin/etcd/:$PATH
 
 # Install uv and create virtualenv
 COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /bin/
-RUN mkdir /opt/dynemo && \
-    uv venv /opt/dynemo/venv --python 3.12
+RUN mkdir /opt/dynamo && \
+    uv venv /opt/dynamo/venv --python 3.12
 
 # Activate virtual environment
-ENV VIRTUAL_ENV=/opt/dynemo/venv
+ENV VIRTUAL_ENV=/opt/dynamo/venv
 ENV PATH="${VIRTUAL_ENV}/bin:${PATH}"
 
 # Install patched vllm - keep this early in Dockerfile to avoid
 # rebuilds from unrelated source code changes
 ARG VLLM_REF="v0.7.2"
-ARG VLLM_PATCH="vllm_${VLLM_REF}-dynemo-kv-disagg-patch.patch"
+ARG VLLM_PATCH="vllm_${VLLM_REF}-dynamo-kv-disagg-patch.patch"
 RUN --mount=type=bind,source=./container/deps/,target=/tmp/deps \
     bash /tmp/deps/vllm/install.sh --patch /tmp/deps/vllm/${VLLM_PATCH} --ref ${VLLM_REF} --install-cmd "uv pip install --editable" --use-precompiled --installation-dir /opt/vllm
 
@@ -92,7 +92,7 @@ RUN cd examples/rust && \
     cp target/release/http /usr/local/bin/ && \
     cp target/release/llmctl /usr/local/bin/
 
-# TODO: Build dynemo-run
+# TODO: Build dynamo-run
 # COPY applications/...
 
 # Generate C bindings for kv cache routing in vLLM
@@ -100,29 +100,29 @@ COPY lib/bindings /workspace/lib/bindings
 RUN cd lib/bindings/c && \
 cargo build --release --locked && cargo doc --no-deps
 
-COPY deploy/dynemo/sdk /workspace/deploy/dynemo/sdk
-# Build dynemo wheel
-RUN source /opt/dynemo/venv/bin/activate && \
+COPY deploy/dynamo/sdk /workspace/deploy/dynamo/sdk
+# Build dynamo wheel
+RUN source /opt/dynamo/venv/bin/activate && \
     uv build --wheel --out-dir /workspace/dist && \
-    uv pip install /workspace/dist/dynemo*cp312*.whl && \
-    cd /workspace/deploy/dynemo/sdk && \
+    uv pip install /workspace/dist/dynamo*cp312*.whl && \
+    cd /workspace/deploy/dynamo/sdk && \
     uv build --wheel --out-dir /workspace/dist && \
-    uv pip install /workspace/dist/dynemo_sdk*any.whl
+    uv pip install /workspace/dist/dynamo_sdk*any.whl
 
 # Package the bindings
-RUN mkdir -p /opt/dynemo/bindings/wheels && \
-    mkdir /opt/dynemo/bindings/lib && \
-    cp dist/dynemo*cp312*.whl /opt/dynemo/bindings/wheels/. && \
-    cp lib/bindings/c/target/release/libdynemo_llm_capi.so /opt/dynemo/bindings/lib/. && \
-    cp -r lib/bindings/c/include /opt/dynemo/bindings/.
+RUN mkdir -p /opt/dynamo/bindings/wheels && \
+    mkdir /opt/dynamo/bindings/lib && \
+    cp dist/dynamo*cp312*.whl /opt/dynamo/bindings/wheels/. && \
+    cp lib/bindings/c/target/release/libdynamo_llm_capi.so /opt/dynamo/bindings/lib/. && \
+    cp -r lib/bindings/c/include /opt/dynamo/bindings/.
 
-# Tell vllm to use the Dynemo LLM C API for KV Cache Routing
-ENV VLLM_KV_CAPI_PATH="/opt/dynemo/bindings/lib/libdynemo_llm_capi.so"
+# Tell vllm to use the Dynamo LLM C API for KV Cache Routing
+ENV VLLM_KV_CAPI_PATH="/opt/dynamo/bindings/lib/libdynamo_llm_capi.so"
 
 # FIXME: Copy more specific folders in for dev/debug after directory restructure
 COPY . /workspace
 
-# FIXME: May want a modification with dynemo-distributed banner on entry
+# FIXME: May want a modification with dynamo banner on entry
 ENTRYPOINT ["/opt/nvidia/nvidia_entrypoint.sh"]
 
 CMD []
@@ -140,10 +140,10 @@ RUN apt update -y && \
     echo "set -g mouse on" >> /root/.tmux.conf
 
 # Set environment variables
-ENV VIRTUAL_ENV=/opt/dynemo/venv
+ENV VIRTUAL_ENV=/opt/dynamo/venv
 ENV PATH="${VIRTUAL_ENV}/bin:${PATH}"
 ENV RAPIDS_LIBUCX_PREFER_SYSTEM_LIBRARY=true
-ENV VLLM_KV_CAPI_PATH="/opt/dynemo/bindings/lib/libdynemo_llm_capi.so"
+ENV VLLM_KV_CAPI_PATH="/opt/dynamo/bindings/lib/libdynamo_llm_capi.so"
 
 # Copy binaries
 COPY --from=dev /usr/local/bin/http /usr/local/bin/http
@@ -170,7 +170,7 @@ COPY examples/python_rs/llm/vllm /workspace/examples/python_rs/llm/vllm
 
 WORKDIR /workspace
 
-# FIXME: May want a modification with dynemo-distributed banner on entry
+# FIXME: May want a modification with dynamo banner on entry
 ENTRYPOINT ["/opt/nvidia/nvidia_entrypoint.sh"]
 
 CMD []

container/Dockerfile.vllm_nixl

@@ -151,11 +151,11 @@ ENV PATH=/usr/local/bin/etcd/:$PATH
 
 # Install uv and create virtualenv
 COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /bin/
-RUN mkdir /opt/dynemo && \
-    uv venv /opt/dynemo/venv --python 3.12
+RUN mkdir /opt/dynamo && \
+    uv venv /opt/dynamo/venv --python 3.12
 
 # Activate virtual environment
-ENV VIRTUAL_ENV=/opt/dynemo/venv
+ENV VIRTUAL_ENV=/opt/dynamo/venv
 ENV PATH="${VIRTUAL_ENV}/bin:${PATH}"
 
 # Common dependencies
@@ -165,7 +165,7 @@ RUN --mount=type=bind,source=./container/deps/requirements.txt,target=/tmp/requi
 # Install patched vllm - keep this early in Dockerfile to avoid
 # rebuilds from unrelated source code changes
 ARG VLLM_REF="v0.7.2"
-ARG VLLM_PATCH="vllm_${VLLM_REF}-dynemo-kv-disagg-patch.patch"
+ARG VLLM_PATCH="vllm_${VLLM_REF}-dynamo-kv-disagg-patch.patch"
 RUN --mount=type=bind,source=./container/deps/,target=/tmp/deps \
     bash /tmp/deps/vllm/install.sh --patch /tmp/deps/vllm/${VLLM_PATCH} --ref ${VLLM_REF} --install-cmd "uv pip install --editable" --use-precompiled --installation-dir /opt/vllm
 
@@ -230,30 +230,29 @@ COPY lib/bindings /workspace/lib/bindings
 RUN cd lib/bindings/c && \
     cargo build --release --locked && cargo doc --no-deps
 
-COPY deploy/dynemo/sdk /workspace/deploy/dynemo/sdk
-# Build dynemo wheel
-RUN source /opt/dynemo/venv/bin/activate && \
+COPY deploy/dynamo/sdk /workspace/deploy/dynamo/sdk
+# Build dynamo wheel
+RUN source /opt/dynamo/venv/bin/activate && \
     uv build --wheel --out-dir /workspace/dist && \
-    uv pip install /workspace/dist/dynemo*cp312*.whl && \
-    cd /workspace/deploy/dynemo/sdk && \
+    uv pip install /workspace/dist/dynamo*cp312*.whl && \
+    cd /workspace/deploy/dynamo/sdk && \
     uv build --wheel --out-dir /workspace/dist && \
-    uv pip install /workspace/dist/dynemo_sdk*any.whl
+    uv pip install /workspace/dist/dynamo_sdk*any.whl
 
 # Package the bindings
-RUN mkdir -p /opt/dynemo/bindings/wheels && \
-    mkdir /opt/dynemo/bindings/lib && \
-    cp dist/dynemo*cp312*.whl /opt/dynemo/bindings/wheels/. && \
-    cp lib/bindings/c/target/release/libdynemo_llm_capi.so /opt/dynemo/bindings/lib/. && \
-    cp -r lib/bindings/c/include /opt/dynemo/bindings/.
+RUN mkdir -p /opt/dynamo/bindings/wheels && \
+    mkdir /opt/dynamo/bindings/lib && \
+    cp dist/dynamo*cp312*.whl /opt/dynamo/bindings/wheels/. && \
+    cp lib/bindings/c/target/release/libdynamo_llm_capi.so /opt/dynamo/bindings/lib/. && \
+    cp -r lib/bindings/c/include /opt/dynamo/bindings/.
 
-# Tell vllm to use the Dynemo LLM C API for KV Cache Routing
-ENV VLLM_KV_CAPI_PATH="/opt/dynemo/bindings/lib/libdynemo_llm_capi.so"
+# Tell vllm to use the Dynamo LLM C API for KV Cache Routing
+ENV VLLM_KV_CAPI_PATH="/opt/dynamo/bindings/lib/libdynamo_llm_capi.so"
 
 # FIXME: Copy more specific folders in for dev/debug after directory restructure
 COPY . /workspace
 
-
-# FIXME: May want a modification with dynemo-distributed banner on entry
+# FIXME: May want a modification with dynamo banner on entry
 ENTRYPOINT ["/opt/nvidia/nvidia_entrypoint.sh"]
 
 CMD []
@@ -271,10 +270,10 @@ RUN apt update -y && \
     echo "set -g mouse on" >> /root/.tmux.conf
 
 # Set environment variables
-ENV VIRTUAL_ENV=/opt/dynemo/venv
+ENV VIRTUAL_ENV=/opt/dynamo/venv
 ENV PATH="${VIRTUAL_ENV}/bin:${PATH}"
 ENV RAPIDS_LIBUCX_PREFER_SYSTEM_LIBRARY=true
-ENV VLLM_KV_CAPI_PATH="/opt/dynemo/bindings/lib/libdynemo_llm_capi.so"
+ENV VLLM_KV_CAPI_PATH="/opt/dynamo/bindings/lib/libdynamo_llm_capi.so"
 
 # Copy binaries
 COPY --from=dev /usr/local/bin/http /usr/local/bin/http
@@ -301,7 +300,7 @@ COPY examples/python_rs/llm/vllm_nixl /workspace/examples/python_rs/llm/vllm_nix
 
 WORKDIR /workspace
 
-# FIXME: May want a modification with dynemo-distributed banner on entry
+# FIXME: May want a modification with dynamo banner on entry
 ENTRYPOINT ["/opt/nvidia/nvidia_entrypoint.sh"]
 
 CMD []

container/deps/clone_tensorrtllm.sh

@@ -16,7 +16,7 @@
 
 TENSORRTLLM_BACKEND_REPO_TAG=
 TENSORRTLLM_BACKEND_REBUILD=
-DYNEMO_LLM_PATH=
+DYNAMO_LLM_PATH=
 GIT_TOKEN=
 GIT_REPO=
 
@@ -43,9 +43,9 @@ get_options() {
 		missing_requirement $1
             fi
             ;;
-    --dynemo-llm-path)
+    --dynamo-llm-path)
             if [ "$2" ]; then
-                DYNEMO_LLM_PATH=$2
+                DYNAMO_LLM_PATH=$2
                 shift
             else
 		missing_requirement $1
@@ -147,7 +147,7 @@ if [ ! -z ${TENSORRTLLM_BACKEND_REBUILD} ]; then
 
     # Build the backend
     (cd inflight_batcher_llm/src \
-        && cmake -DCMAKE_INSTALL_PREFIX:PATH=`pwd`/install -DUSE_CXX11_ABI=1 -DDYNEMO_LLM_PATH=$DYNEMO_LLM_PATH .. \
+        && cmake -DCMAKE_INSTALL_PREFIX:PATH=`pwd`/install -DUSE_CXX11_ABI=1 -DDYNAMO_LLM_PATH=$DYNAMO_LLM_PATH .. \
         && make install \
         && cp libtriton_tensorrtllm.so /opt/tritonserver/backends/tensorrtllm/ \
         && cp trtllmExecutorWorker /opt/tritonserver/backends/tensorrtllm/ \

container/deps/vllm/vllm_v0.7.2-dynemo-kv-disagg-patch.patch → container/deps/vllm/vllm_v0.7.2-dynamo-kv-disagg-patch.patch

 diff --git a/vllm/config.py b/vllm/config.py
-index 9ba49757..3ec4bbab 100644
+index 9ba49757..5e1cf249 100644
 --- a/vllm/config.py
 +++ b/vllm/config.py
 @@ -2620,6 +2620,9 @@ class KVTransferConfig(BaseModel):
@@ -41,7 +41,7 @@ index 9ba49757..3ec4bbab 100644
                  f"and `kv_both`")
  
 -        if self.kv_connector is not None and self.kv_role is None:
-+        if self.kv_connector is not None and self.kv_connector != "DynemoNixlConnector" and self.kv_role is None:
++        if self.kv_connector is not None and self.kv_connector != "DynamoNixlConnector" and self.kv_role is None:
              raise ValueError("Please specify kv_disagg_role when kv_connector "
                               "is set, supported roles are `kv_producer`, "
                               "`kv_consumer`, and `kv_both`")
@@ -54,7 +54,7 @@ index 9ba49757..3ec4bbab 100644
      def need_kv_parallel_group(self) -> bool:
          # for those database-based connector, vLLM does not need to create
          # parallel group, and in that case the kv parallel size will be 1.
-+        if self.kv_connector == "DynemoNixlConnector":
++        if self.kv_connector == "DynamoNixlConnector":
 +            return False
          return self.kv_connector is not None and self.kv_parallel_size > 1
  
@@ -271,7 +271,7 @@ index c5b3b04f..c72001f7 100644
          self.block_tables: Dict[SeqId, BlockTable] = {}
 diff --git a/vllm/core/event_manager.py b/vllm/core/event_manager.py
 new file mode 100644
-index 00000000..8699ca06
+index 00000000..d3706700
 --- /dev/null
 +++ b/vllm/core/event_manager.py
 @@ -0,0 +1,102 @@
@@ -287,7 +287,7 @@ index 00000000..8699ca06
 +logger = logging.getLogger(__name__)
 +
 +
-+class DynemoResult:
++class DynamoResult:
 +    OK = 0
 +    ERR = 1
 +
@@ -300,12 +300,12 @@ index 00000000..8699ca06
 +
 +        try:
 +            self.lib = ctypes.CDLL(lib_path)
-+            self.lib.dynemo_llm_init.argtypes = [c_char_p, c_char_p, c_int64]
-+            self.lib.dynemo_llm_init.restype = c_uint32
++            self.lib.dynamo_llm_init.argtypes = [c_char_p, c_char_p, c_int64]
++            self.lib.dynamo_llm_init.restype = c_uint32
 +
-+            result = self.lib.dynemo_llm_init(namespace.encode(),
++            result = self.lib.dynamo_llm_init(namespace.encode(),
 +                                              component.encode(), worker_id)
-+            if result == DynemoResult.OK:
++            if result == DynamoResult.OK:
 +                logger.info(
 +                    "KVCacheEventManager initialized successfully. Ready to publish KV Cache Events"
 +                )
@@ -316,7 +316,7 @@ index 00000000..8699ca06
 +            print(f"Failed to load {lib_path}")
 +            raise e
 +
-+        self.lib.dynemo_kv_event_publish_stored.argtypes = [
++        self.lib.dynamo_kv_event_publish_stored.argtypes = [
 +            ctypes.c_uint64,  # event_id
 +            ctypes.POINTER(ctypes.c_uint32),  # token_ids
 +            ctypes.POINTER(ctypes.c_size_t),  # num_block_tokens
@@ -325,14 +325,14 @@ index 00000000..8699ca06
 +            ctypes.POINTER(ctypes.c_uint64),  # parent_hash
 +            ctypes.c_uint64,  # lora_id
 +        ]
-+        self.lib.dynemo_kv_event_publish_stored.restype = ctypes.c_uint32  # dynemo_llm_result_t
++        self.lib.dynamo_kv_event_publish_stored.restype = ctypes.c_uint32  # dynamo_llm_result_t
 +
-+        self.lib.dynemo_kv_event_publish_removed.argtypes = [
++        self.lib.dynamo_kv_event_publish_removed.argtypes = [
 +            ctypes.c_uint64,  # event_id
 +            ctypes.POINTER(ctypes.c_uint64),  # block_ids
 +            ctypes.c_size_t,  # num_blocks
 +        ]
-+        self.lib.dynemo_kv_event_publish_removed.restype = ctypes.c_uint32  # dynemo_llm_result_t
++        self.lib.dynamo_kv_event_publish_removed.restype = ctypes.c_uint32  # dynamo_llm_result_t
 +
 +        self.event_id_counter = 0
 +
@@ -346,7 +346,7 @@ index 00000000..8699ca06
 +                       if parent is not None else None)
 +
 +        # Publish the event
-+        result = self.lib.dynemo_kv_event_publish_stored(
++        result = self.lib.dynamo_kv_event_publish_stored(
 +            self.event_id_counter,  # uint64_t event_id
 +            token_ids_arr,  # const uint32_t *token_ids
 +            num_block_tokens,  # const uintptr_t *num_block_tokens
@@ -356,7 +356,7 @@ index 00000000..8699ca06
 +            0,  # uint64_t lora_id
 +        )
 +
-+        if result == DynemoResult.OK:
++        if result == DynamoResult.OK:
 +            logger.debug(f"Store - Published KV Event: {block.content_hash}")
 +        else:
 +            logger.debug(
@@ -365,13 +365,13 @@ index 00000000..8699ca06
 +        self.event_id_counter += 1
 +
 +    def enqueue_removed_event(self, block_hash: PrefixHash):
-+        result = self.lib.dynemo_kv_event_publish_removed(
++        result = self.lib.dynamo_kv_event_publish_removed(
 +            self.event_id_counter,
 +            (ctypes.c_uint64 * 1)(block_hash),
 +            1,
 +        )
 +
-+        if result == DynemoResult.OK:
++        if result == DynamoResult.OK:
 +            logger.debug(f"Remove - Published KV Event: {block_hash}")
 +        else:
 +            logger.debug(f"Remove - Failed to Publish KV Event: {block_hash}")
@@ -764,7 +764,7 @@ index 00000000..9b938039
 \ No newline at end of file
 diff --git a/vllm/distributed/device_communicators/nixl.py b/vllm/distributed/device_communicators/nixl.py
 new file mode 100644
-index 00000000..523d58d4
+index 00000000..87020367
 --- /dev/null
 +++ b/vllm/distributed/device_communicators/nixl.py
 @@ -0,0 +1,405 @@
@@ -799,7 +799,7 @@ index 00000000..523d58d4
 +    num_blocks: int
 +
 +
-+class DynemoNixlConnector:
++class DynamoNixlConnector:
 +    def __init__(self, vllm_config: VllmConfig, engine_id: str, rank: int):
 +        self.vllm_config = vllm_config
 +        if NixlWrapper is None:
@@ -1173,11 +1173,11 @@ index 00000000..523d58d4
 +            else:
 +                self._transfers[req_id] = running_reqs
 +        return done_req_ids
-diff --git a/vllm/distributed/kv_transfer/kv_connector/dynemo_connector.py b/vllm/distributed/kv_transfer/kv_connector/dynemo_connector.py
+diff --git a/vllm/distributed/kv_transfer/kv_connector/dynamo_connector.py b/vllm/distributed/kv_transfer/kv_connector/dynamo_connector.py
 new file mode 100644
-index 00000000..2319867a
+index 00000000..7b3344f8
 --- /dev/null
-+++ b/vllm/distributed/kv_transfer/kv_connector/dynemo_connector.py
++++ b/vllm/distributed/kv_transfer/kv_connector/dynamo_connector.py
 @@ -0,0 +1,350 @@
 +# SPDX-License-Identifier: Apache-2.0
 +"""
@@ -1209,7 +1209,7 @@ index 00000000..2319867a
 +logger = init_logger(__name__)
 +
 +
-+class DynemoConnector(KVConnectorBase):
++class DynamoConnector(KVConnectorBase):
 +
 +    def __init__(
 +        self,
@@ -1223,16 +1223,16 @@ index 00000000..2319867a
 +        self.tp_size = config.parallel_config.tensor_parallel_size
 +        self.rank = rank
 +
-+        if self.config.kv_connector != "DynemoNcclConnector":
-+            raise NotImplementedError("Only DynemoNcclConnector is supported by the DynemoConnector class")
++        if self.config.kv_connector != "DynamoNcclConnector":
++            raise NotImplementedError("Only DynamoNcclConnector is supported by the DynamoConnector class")
 +
 +        from vllm.distributed.kv_transfer.kv_pipe.pynccl_pipe import (
 +            PyNcclPipe)
-+        from vllm.distributed.kv_transfer.kv_pipe.dynemo_nccl_pipe import (
-+            DynemoNcclDataPlane)
++        from vllm.distributed.kv_transfer.kv_pipe.dynamo_nccl_pipe import (
++            DynamoNcclDataPlane)
 +        
 +        logger.info(
-+            "Initializing DynemoNcclConnector under kv_transfer_config %s",
++            "Initializing DynamoNcclConnector under kv_transfer_config %s",
 +            self.config)
 +
 +        self.lookup_buffer_size = self.config.kv_buffer_size
@@ -1264,7 +1264,7 @@ index 00000000..2319867a
 +            port_offset=port_offset_base,
 +        )
 +
-+        self.data_plane = DynemoNcclDataPlane(
++        self.data_plane = DynamoNcclDataPlane(
 +            data_pipe=self.data_pipe,
 +            port=self._get_data_plane_port(self.global_kv_rank),
 +        )
@@ -1530,7 +1530,7 @@ index 00000000..2319867a
 +        self.config.kv_consumers_pipeline_parallel_size = kv_config_enhanced["kv_consumers_pipeline_parallel_size"]
 +        self.config.kv_producers_parallel_size = kv_config_enhanced["kv_producers_parallel_size"]
 diff --git a/vllm/distributed/kv_transfer/kv_connector/factory.py b/vllm/distributed/kv_transfer/kv_connector/factory.py
-index fe480533..f4775663 100644
+index fe480533..c82fda80 100644
 --- a/vllm/distributed/kv_transfer/kv_connector/factory.py
 +++ b/vllm/distributed/kv_transfer/kv_connector/factory.py
 @@ -27,13 +27,13 @@ class KVConnectorFactory:
@@ -1555,11 +1555,11 @@ index fe480533..f4775663 100644
      "SimpleConnector")
 +
 +KVConnectorFactory.register_connector(
-+    "DynemoNcclConnector",
-+    "vllm.distributed.kv_transfer.kv_connector.dynemo_connector",
-+    "DynemoConnector")
++    "DynamoNcclConnector",
++    "vllm.distributed.kv_transfer.kv_connector.dynamo_connector",
++    "DynamoConnector")
 diff --git a/vllm/distributed/kv_transfer/kv_connector/simple_connector.py b/vllm/distributed/kv_transfer/kv_connector/simple_connector.py
-index 2033e976..e0537903 100644
+index 2033e976..ddebb68e 100644
 --- a/vllm/distributed/kv_transfer/kv_connector/simple_connector.py
 +++ b/vllm/distributed/kv_transfer/kv_connector/simple_connector.py
 @@ -8,13 +8,15 @@ MooncakePipe.
@@ -1886,7 +1886,7 @@ index 2033e976..e0537903 100644
 +                world_group.broadcast_object(kv_config_enhanced)
 +
 +            else:
-+                raise NotImplementedError("MooncakeConnector is not supported in Dynemo patch")
++                raise NotImplementedError("MooncakeConnector is not supported in Dynamo patch")
 +        else:
 +            kv_config_enhanced = world_group.broadcast_object()
 +        logger.info("kv_config_enhanced: %s", kv_config_enhanced)
@@ -2175,11 +2175,11 @@ index 40589fb3..da2829cf 100644
          """Receive a tensor (can be None) from the pipeline.
  
          Returns:
-diff --git a/vllm/distributed/kv_transfer/kv_pipe/dynemo_nccl_pipe.py b/vllm/distributed/kv_transfer/kv_pipe/dynemo_nccl_pipe.py
+diff --git a/vllm/distributed/kv_transfer/kv_pipe/dynamo_nccl_pipe.py b/vllm/distributed/kv_transfer/kv_pipe/dynamo_nccl_pipe.py
 new file mode 100644
-index 00000000..58d0d28c
+index 00000000..3ee0fa78
 --- /dev/null
-+++ b/vllm/distributed/kv_transfer/kv_pipe/dynemo_nccl_pipe.py
++++ b/vllm/distributed/kv_transfer/kv_pipe/dynamo_nccl_pipe.py
 @@ -0,0 +1,124 @@
 +import logging
 +import threading
@@ -2195,7 +2195,7 @@ index 00000000..58d0d28c
 +logger = logging.getLogger(__name__)
 +
 +
-+class DynemoNcclDataPlane:
++class DynamoNcclDataPlane:
 +    def __init__(
 +        self,
 +        data_pipe: PyNcclPipe,
@@ -2531,7 +2531,7 @@ index 321902d1..b8937ef8 100644
  
  def ensure_model_parallel_initialized(
 diff --git a/vllm/engine/llm_engine.py b/vllm/engine/llm_engine.py
-index d82d9ad9..cc02b029 100644
+index d82d9ad9..53cace75 100644
 --- a/vllm/engine/llm_engine.py
 +++ b/vllm/engine/llm_engine.py
 @@ -2,13 +2,17 @@
@@ -2614,7 +2614,7 @@ index d82d9ad9..cc02b029 100644
  
 +        self.engine_id = str(uuid.uuid4())
 +        self._nixl_agents_names: Optional[List[str]] = None
-+        if self.vllm_config.kv_transfer_config is not None and self.vllm_config.kv_transfer_config.kv_connector == "DynemoNixlConnector":
++        if self.vllm_config.kv_transfer_config is not None and self.vllm_config.kv_transfer_config.kv_connector == "DynamoNixlConnector":
 +            self._nixl_agents_names = self._initialize_nixl()
 +
 +        self._request_notif_counter = defaultdict(lambda: -self.parallel_config.tensor_parallel_size)
@@ -2946,7 +2946,7 @@ index 3cf1850e..6b90ece7 100644
 +    kv_active_blocks: int
 +    kv_total_blocks: int
 diff --git a/vllm/engine/multiprocessing/client.py b/vllm/engine/multiprocessing/client.py
-index 85b5f31e..3f8b8fad 100644
+index 85b5f31e..da207947 100644
 --- a/vllm/engine/multiprocessing/client.py
 +++ b/vllm/engine/multiprocessing/client.py
 @@ -8,6 +8,7 @@ from typing import (Any, AsyncGenerator, Dict, Iterator, List, Mapping,
@@ -3028,7 +3028,7 @@ index 85b5f31e..3f8b8fad 100644
 +    
 +    @property
 +    def using_nixl_connector(self) -> bool:
-+        return self.vllm_config.kv_transfer_config is not None and self.vllm_config.kv_transfer_config.kv_connector == "DynemoNixlConnector"
++        return self.vllm_config.kv_transfer_config is not None and self.vllm_config.kv_transfer_config.kv_connector == "DynamoNixlConnector"
 +
      @staticmethod
      def is_unsupported_config(engine_args: AsyncEngineArgs):
@@ -3656,7 +3656,7 @@ index 534b9e60..18675d2f 100644
      @property
      def is_first_multi_step(self) -> bool:
 diff --git a/vllm/worker/model_runner.py b/vllm/worker/model_runner.py
-index 12baecde..489d3b77 100644
+index 12baecde..a3f2c464 100644
 --- a/vllm/worker/model_runner.py
 +++ b/vllm/worker/model_runner.py
 @@ -1824,6 +1824,9 @@ class ModelRunner(GPUModelRunnerBase[ModelInputForGPUWithSamplingMetadata]):
@@ -3664,7 +3664,7 @@ index 12baecde..489d3b77 100644
          if self.vllm_config.kv_transfer_config is None:
              return False
 +        
-+        if self.vllm_config.kv_transfer_config.kv_connector == "DynemoNixlConnector":
++        if self.vllm_config.kv_transfer_config.kv_connector == "DynamoNixlConnector":
 +            return False
  
          prefill_meta = model_input.attn_metadata.prefill_metadata
@@ -3674,13 +3674,13 @@ index 12baecde..489d3b77 100644
          if self.vllm_config.kv_transfer_config is None:
              return False
 +        
-+        if self.vllm_config.kv_transfer_config.kv_connector == "DynemoNixlConnector":
++        if self.vllm_config.kv_transfer_config.kv_connector == "DynamoNixlConnector":
 +            return False
  
          prefill_meta = model_input.attn_metadata.prefill_metadata
  
 diff --git a/vllm/worker/worker.py b/vllm/worker/worker.py
-index 582aa460..e4ed902e 100644
+index 582aa460..36a21d10 100644
 --- a/vllm/worker/worker.py
 +++ b/vllm/worker/worker.py
 @@ -2,7 +2,7 @@
@@ -3696,7 +3696,7 @@ index 582aa460..e4ed902e 100644
  from vllm.worker.pooling_model_runner import PoolingModelRunner
  from vllm.worker.worker_base import (LocalOrDistributedWorkerBase, WorkerBase,
                                       WorkerInput)
-+from vllm.distributed.device_communicators.nixl import DynemoNixlConnector
++from vllm.distributed.device_communicators.nixl import DynamoNixlConnector
 +
  
  logger = init_logger(__name__)
@@ -3710,7 +3710,7 @@ index 582aa460..e4ed902e 100644
 +        # TODO ptarasiewicz nixl can also support DRAM
 +        assert self.device_config.device_type == "cuda", "Currently only CUDA is supported for Nixl connector"
 +
-+        self.nixl_connector = DynemoNixlConnector(self.vllm_config, engine_id, self.local_rank) # TODO ptarasiewicz: rank or local_rank?
++        self.nixl_connector = DynamoNixlConnector(self.vllm_config, engine_id, self.local_rank) # TODO ptarasiewicz: rank or local_rank?
 +        assert len(self.cache_engine) == 1, "Only one cache engine is supported for now"
 +        self.nixl_connector.register_kv_caches(self.cache_engine[0].gpu_cache)
 +        return self.nixl_connector.agent_name
@@ -3766,7 +3766,7 @@ index 582aa460..e4ed902e 100644
  
      @torch.inference_mode()
 diff --git a/vllm/worker/worker_base.py b/vllm/worker/worker_base.py
-index 819b81fb..8dfdadde 100644
+index 819b81fb..ff43dadc 100644
 --- a/vllm/worker/worker_base.py
 +++ b/vllm/worker/worker_base.py
 @@ -9,6 +9,7 @@ from typing import Any, Dict, List, Optional, Set, Tuple, Type, Union
@@ -3781,7 +3781,7 @@ index 819b81fb..8dfdadde 100644
  from vllm.worker.model_runner_base import (BroadcastableModelInput,
                                             ModelRunnerBase,
                                             ModelRunnerInputBase)
-+from vllm.distributed.device_communicators.nixl import DynemoNixlConnector
++from vllm.distributed.device_communicators.nixl import DynamoNixlConnector
  
  logger = init_logger(__name__)
  
@@ -3789,7 +3789,7 @@ index 819b81fb..8dfdadde 100644
          from vllm.platforms import current_platform
          self.current_platform = current_platform
  
-+        self.nixl_connector: Optional[DynemoNixlConnector] = None
++        self.nixl_connector: Optional[DynamoNixlConnector] = None
 +
      @abstractmethod
      def init_device(self) -> None:

deploy/Kubernetes/common/chart/Chart.yaml

@@ -15,7 +15,7 @@
 
 apiVersion: v2
 appVersion: 1.0.0
-description: Distributed Neural Models (dynemo) Component
+description: Distributed Neural Models (dynamo) Component
 icon: https://www.nvidia.com/content/dam/en-zz/Solutions/about-nvidia/logo-and-brand/01-nvidia-logo-vert-500x200-2c50-d@2x.png
-name: dynemo_component
+name: dynamo_component
 version: 1.0.0

deploy/Kubernetes/common/chart/templates/_helpers.tpl

@@ -15,7 +15,7 @@
 
 # Annotation Groups
 {{- define "nvidia.annotations.default" }}
-dynemo: "{{ .Release.Name }}.{{ .Chart.AppVersion | default "0.0" }}"
+dynamo: "{{ .Release.Name }}.{{ .Chart.AppVersion | default "0.0" }}"
 {{-   with .Values.kubernetes }}
 {{-     with .annotations }}
 {{        toYaml . }}
@@ -54,7 +54,7 @@ app.kubernetes.io/instance: {{ .Release.Name }}
 {{- end }}
 
 {{- define "nvidia.label.appManagedBy" }}
-{{-   $service_name := "dynemo" }}
+{{-   $service_name := "dynamo" }}
 {{-   with .Release.Service }}
 {{-     $service_name = . }}
 {{-   end }}
@@ -66,7 +66,7 @@ app.kubernetes.io/name: {{ required "Property '.component.name' is required." .V
 {{- end }}
 
 {{- define "nvidia.label.appPartOf" }}
-{{-   $part_of := "dynemo" }}
+{{-   $part_of := "dynamo" }}
 {{-   with .Values.kubernetes }}
 {{-     with .partOf }}
 {{-       $part_of = . }}