refactor: rename triton_distributed to dynemo (#22)

Co-authored-by: Graham King <grahamk@nvidia.com>

examples/python_rs/llm/vllm_nixl/worker.py

@@ -33,11 +33,7 @@ from vllm.entrypoints.openai.serving_chat import OpenAIServingChat
 from vllm.entrypoints.openai.serving_models import BaseModelPath, OpenAIServingModels
 from vllm.remote_prefill import RemotePrefillParams, RemotePrefillRequest
 
-from triton_distributed.runtime import (
-    DistributedRuntime,
-    triton_endpoint,
-    triton_worker,
-)
+from dynemo.runtime import DistributedRuntime, dynemo_endpoint, dynemo_worker
 
 
 class RequestHandler:
@@ -87,7 +83,7 @@ class RequestHandler:
 
         return callback
 
-    @triton_endpoint(ChatCompletionRequest, ChatCompletionStreamResponse)
+    @dynemo_endpoint(ChatCompletionRequest, ChatCompletionStreamResponse)
     async def generate(self, request):
         if not self.initialized:
             await self.init()
@@ -113,7 +109,7 @@ class RequestHandler:
             yield response
 
 
-@triton_worker()
+@dynemo_worker()
 async def worker(runtime: DistributedRuntime, engine_args: AsyncEngineArgs):
     component = runtime.namespace("test-nixl").component("vllm")
     await component.create_service()

examples/rust/Cargo.lock

@@ -955,6 +955,99 @@ dependencies = [
  "syn 2.0.98",
 ]
 
+[[package]]
+name = "dynemo-llm"
+version = "0.2.1"
+dependencies = [
+ "anyhow",
+ "async-openai",
+ "async-stream",
+ "async-trait",
+ "axum 0.8.1",
+ "bindgen",
+ "blake3",
+ "bs62",
+ "bytes",
+ "chrono",
+ "cmake",
+ "derive_builder",
+ "dynemo-runtime",
+ "either",
+ "erased-serde",
+ "futures",
+ "galil-seiferas",
+ "indexmap 2.7.1",
+ "itertools 0.14.0",
+ "libc",
+ "minijinja",
+ "minijinja-contrib",
+ "prometheus",
+ "pyo3",
+ "regex",
+ "semver",
+ "serde",
+ "serde-pickle",
+ "serde_json",
+ "serde_repr",
+ "strum",
+ "thiserror 2.0.11",
+ "tokenizers",
+ "tokio",
+ "tokio-stream",
+ "tokio-util",
+ "toktrie",
+ "toktrie_hf_tokenizers",
+ "tracing",
+ "unicode-segmentation",
+ "uuid",
+ "validator",
+ "xxhash-rust",
+]
+
+[[package]]
+name = "dynemo-runtime"
+version = "0.2.1"
+dependencies = [
+ "anyhow",
+ "async-nats",
+ "async-once-cell",
+ "async-stream",
+ "async-trait",
+ "async_zmq",
+ "blake3",
+ "bytes",
+ "chrono",
+ "derive-getters",
+ "derive_builder",
+ "educe",
+ "either",
+ "etcd-client",
+ "figment",
+ "futures",
+ "humantime",
+ "local-ip-address",
+ "log",
+ "nid",
+ "nix",
+ "nuid",
+ "once_cell",
+ "prometheus",
+ "rand",
+ "regex",
+ "serde",
+ "serde_json",
+ "socket2",
+ "thiserror 1.0.69",
+ "tokio",
+ "tokio-stream",
+ "tokio-util",
+ "tracing",
+ "tracing-subscriber",
+ "uuid",
+ "validator",
+ "xxhash-rust",
+]
+
 [[package]]
 name = "ed25519"
 version = "2.2.3"
@@ -1370,7 +1463,7 @@ checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea"
 name = "hello_world"
 version = "0.2.0"
 dependencies = [
- "triton-distributed-runtime",
+ "dynemo-runtime",
 ]
 
 [[package]]
@@ -1395,11 +1488,11 @@ name = "http"
 version = "0.2.0"
 dependencies = [
  "clap",
+ "dynemo-llm",
+ "dynemo-runtime",
  "serde",
  "serde_json",
  "tokio",
- "triton-distributed-llm",
- "triton-distributed-runtime",
 ]
 
 [[package]]
@@ -1895,13 +1988,13 @@ name = "llmctl"
 version = "0.2.0"
 dependencies = [
  "clap",
+ "dynemo-llm",
+ "dynemo-runtime",
  "serde",
  "serde_json",
  "tabled",
  "tokio",
  "tracing",
- "triton-distributed-llm",
- "triton-distributed-runtime",
 ]
 
 [[package]]
@@ -3297,11 +3390,11 @@ dependencies = [
 name = "service_metrics"
 version = "0.2.0"
 dependencies = [
+ "dynemo-runtime",
  "futures",
  "serde",
  "serde_json",
  "tokio",
- "triton-distributed-runtime",
 ]
 
 [[package]]
@@ -4000,99 +4093,6 @@ dependencies = [
  "tracing-serde",
 ]
 
-[[package]]
-name = "triton-distributed-llm"
-version = "0.2.1"
-dependencies = [
- "anyhow",
- "async-openai",
- "async-stream",
- "async-trait",
- "axum 0.8.1",
- "bindgen",
- "blake3",
- "bs62",
- "bytes",
- "chrono",
- "cmake",
- "derive_builder",
- "either",
- "erased-serde",
- "futures",
- "galil-seiferas",
- "indexmap 2.7.1",
- "itertools 0.14.0",
- "libc",
- "minijinja",
- "minijinja-contrib",
- "prometheus",
- "pyo3",
- "regex",
- "semver",
- "serde",
- "serde-pickle",
- "serde_json",
- "serde_repr",
- "strum",
- "thiserror 2.0.11",
- "tokenizers",
- "tokio",
- "tokio-stream",
- "tokio-util",
- "toktrie",
- "toktrie_hf_tokenizers",
- "tracing",
- "triton-distributed-runtime",
- "unicode-segmentation",
- "uuid",
- "validator",
- "xxhash-rust",
-]
-
-[[package]]
-name = "triton-distributed-runtime"
-version = "0.2.1"
-dependencies = [
- "anyhow",
- "async-nats",
- "async-once-cell",
- "async-stream",
- "async-trait",
- "async_zmq",
- "blake3",
- "bytes",
- "chrono",
- "derive-getters",
- "derive_builder",
- "educe",
- "either",
- "etcd-client",
- "figment",
- "futures",
- "humantime",
- "local-ip-address",
- "log",
- "nid",
- "nix",
- "nuid",
- "once_cell",
- "prometheus",
- "rand",
- "regex",
- "serde",
- "serde_json",
- "socket2",
- "thiserror 1.0.69",
- "tokio",
- "tokio-stream",
- "tokio-util",
- "tracing",
- "tracing-subscriber",
- "uuid",
- "validator",
- "xxhash-rust",
-]
-
 [[package]]
 name = "try-lock"
 version = "0.2.5"

examples/rust/Cargo.toml

@@ -27,14 +27,14 @@ version = "0.2.0"
 edition = "2021"
 authors = ["NVIDIA"]
 license = "Apache-2.0"
-homepage = "https://github.com/triton-inference-server/triton_distributed"
-repository = "https://github.com/triton-inference-server/triton_distributed"
+homepage = "https://github.com/dynemo-ai/dynemo"
+repository = "https://github.com/dynemo-ai/dynemo.git"
 
 
 [workspace.dependencies]
 # local or crates.io
-triton-distributed-runtime = { path = "../../lib/runtime" }
-triton-distributed-llm = { path = "../../lib/llm" }
+dynemo-runtime = { path = "../../lib/runtime" }
+dynemo-llm = { path = "../../lib/llm" }
 
 # crates.io
 anyhow = { version = "1" }

examples/rust/hello_world/Cargo.toml

@@ -22,6 +22,6 @@ license.workspace = true
 homepage.workspace = true
 
 [dependencies]
-triton-distributed-runtime = { workspace = true }
+dynemo-runtime = { workspace = true }
 
 # third-party

examples/rust/hello_world/src/bin/client.rs

@@ -13,11 +13,11 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use hello_world::DEFAULT_NAMESPACE;
-use triton_distributed_runtime::{
+use dynemo_runtime::{
     logging, protocols::annotated::Annotated, stream::StreamExt, DistributedRuntime, Result,
     Runtime, Worker,
 };
+use hello_world::DEFAULT_NAMESPACE;
 
 fn main() -> Result<()> {
     logging::init();

examples/rust/hello_world/src/bin/server.rs

@@ -13,9 +13,7 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use hello_world::DEFAULT_NAMESPACE;
-use std::sync::Arc;
-use triton_distributed_runtime::{
+use dynemo_runtime::{
     logging,
     pipeline::{
         async_trait, network::Ingress, AsyncEngine, AsyncEngineContextProvider, Error, ManyOut,
@@ -24,6 +22,8 @@ use triton_distributed_runtime::{
     protocols::annotated::Annotated,
     stream, DistributedRuntime, Result, Runtime, Worker,
 };
+use hello_world::DEFAULT_NAMESPACE;
+use std::sync::Arc;
 
 fn main() -> Result<()> {
     logging::init();

examples/rust/hello_world/src/lib.rs

@@ -13,4 +13,4 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-pub const DEFAULT_NAMESPACE: &str = "triton-init";
+pub const DEFAULT_NAMESPACE: &str = "dynemo";

examples/rust/http/Cargo.toml

@@ -24,8 +24,8 @@ homepage.workspace = true
 repository.workspace = true
 
 [dependencies]
-triton-distributed-runtime = { workspace = true}
-triton-distributed-llm = { workspace = true}
+dynemo-runtime = { workspace = true}
+dynemo-llm = { workspace = true}
 clap = { version = "4.5", features = ["derive"] }
 
 serde = { workspace = true }

examples/rust/http/src/main.rs

@@ -16,14 +16,14 @@
 use clap::Parser;
 use std::sync::Arc;
 
-use triton_distributed_llm::{
+use dynemo_llm::{
     http::service::{
         discovery::{model_watcher, ModelWatchState},
         service_v2::HttpService,
     },
     model_type::ModelType,
 };
-use triton_distributed_runtime::{
+use dynemo_runtime::{
     logging, transports::etcd::PrefixWatcher, DistributedRuntime, Result, Runtime, Worker,
 };
 

examples/rust/llmctl/Cargo.toml

@@ -23,8 +23,8 @@ homepage.workspace = true
 repository.workspace = true
 
 [dependencies]
-triton-distributed-runtime = { workspace = true}
-triton-distributed-llm = { workspace = true}
+dynemo-runtime = { workspace = true}
+dynemo-llm = { workspace = true}
 
 serde = { workspace = true }
 serde_json = { workspace = true }

examples/rust/llmctl/src/main.rs

@@ -16,8 +16,8 @@
 use clap::{Parser, Subcommand};
 use tracing as log;
 
-use triton_distributed_llm::{http::service::discovery::ModelEntry, model_type::ModelType};
-use triton_distributed_runtime::{
+use dynemo_llm::{http::service::discovery::ModelEntry, model_type::ModelType};
+use dynemo_runtime::{
     distributed::DistributedConfig, logging, protocols::Endpoint, raise, DistributedRuntime,
     Result, Runtime, Worker,
 };

examples/rust/service_metrics/Cargo.toml

@@ -23,10 +23,10 @@ homepage.workspace = true
 repository.workspace = true
 
 [dependencies]
-triton-distributed-runtime = { workspace = true }
+dynemo-runtime = { workspace = true }
 
 # third-party
 futures = { workspace = true }
 serde = { workspace = true }
 serde_json = { workspace = true }
-tokio = { workspace = true }
\ No newline at end of file
+tokio = { workspace = true }

examples/rust/service_metrics/README.md

@@ -4,14 +4,14 @@ This example extends the hello_world example by calling the `scrape_service` met
 with the service name for the request response the client just issued a request.
 
 ```bash
-TRD_LOG=debug cargo run --bin server
+DYN_LOG=debug cargo run --bin server
 ```
 
 The client can now observe some basic statistics about each instance of the service
 begin hosted.
 
 ```bash
-TRD_LOG=info cargo run --bin client
+DYN_LOG=info cargo run --bin client
 ```
 
 ## Example Output
@@ -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: "triton_init_backend_720278f8", id: "eOHMc4ndRw8s5flv4WOZx7", version: "0.0.1", started: "2025-02-26T18:54:04.917294605Z", endpoints: [EndpointInfo { name: "triton_init_backend_720278f8-generate-694d951a80e06abf", subject: "triton_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: "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")})) }] }] }
 ```
 
 Note the following stats in the output demonstrate the custom

examples/rust/service_metrics/src/bin/client.rs

@@ -16,7 +16,7 @@
 use futures::StreamExt;
 use service_metrics::DEFAULT_NAMESPACE;
 
-use triton_distributed_runtime::{
+use dynemo_runtime::{
     logging, protocols::annotated::Annotated, utils::Duration, DistributedRuntime, Result, Runtime,
     Worker,
 };

examples/rust/service_metrics/src/bin/server.rs

@@ -15,8 +15,7 @@
 
 use service_metrics::{MyStats, DEFAULT_NAMESPACE};
 
-use std::sync::Arc;
-use triton_distributed_runtime::{
+use dynemo_runtime::{
     logging,
     pipeline::{
         async_trait, network::Ingress, AsyncEngine, AsyncEngineContextProvider, Error, ManyOut,
@@ -25,6 +24,7 @@ use triton_distributed_runtime::{
     protocols::annotated::Annotated,
     stream, DistributedRuntime, Result, Runtime, Worker,
 };
+use std::sync::Arc;
 
 fn main() -> Result<()> {
     logging::init();

examples/rust/service_metrics/src/lib.rs

@@ -15,7 +15,7 @@
 
 use serde::{Deserialize, Serialize};
 
-pub const DEFAULT_NAMESPACE: &str = "triton-init";
+pub const DEFAULT_NAMESPACE: &str = "dynemo";
 
 #[derive(Serialize, Deserialize)]
 // Dummy Stats object to demonstrate how to attach a custom stats handler

launch/dynemo-run/Cargo.lock

@@ -1374,6 +1374,58 @@ dependencies = [
  "reborrow",
 ]
 
+[[package]]
+name = "dynemo-llm"
+version = "0.2.1"
+dependencies = [
+ "anyhow",
+ "async-openai",
+ "async-stream",
+ "async-trait",
+ "async_zmq",
+ "axum 0.8.1",
+ "bindgen 0.70.1",
+ "blake3",
+ "bs62",
+ "bytes",
+ "chrono",
+ "cmake",
+ "derive_builder",
+ "dynemo-runtime",
+ "either",
+ "erased-serde",
+ "futures",
+ "galil-seiferas",
+ "indexmap 2.7.1",
+ "itertools 0.14.0",
+ "libc",
+ "llama-cpp-2",
+ "minijinja",
+ "minijinja-contrib",
+ "mistralrs",
+ "prometheus",
+ "pyo3",
+ "regex",
+ "semver",
+ "serde",
+ "serde-pickle",
+ "serde_json",
+ "serde_repr",
+ "strum 0.27.1",
+ "thiserror 2.0.11",
+ "tokenizers",
+ "tokio",
+ "tokio-stream",
+ "tokio-util",
+ "toktrie 0.6.28",
+ "toktrie_hf_tokenizers 0.6.28",
+ "tracing",
+ "unicode-segmentation",
+ "uuid 1.14.0",
+ "validator",
+ "xxhash-rust",
+]
+
 [[package]]
 name = "dynemo-run"
 version = "0.1.0"
@@ -1384,6 +1436,8 @@ dependencies = [
  "async-trait",
  "clap",
  "dialoguer",
+ "dynemo-llm",
+ "dynemo-runtime",
  "futures",
  "futures-util",
  "libc",
@@ -1395,8 +1449,50 @@ dependencies = [
  "tokio-util",
  "tracing",
  "tracing-subscriber",
- "triton-distributed-llm",
- "triton-distributed-runtime",
+]
+
+[[package]]
+name = "dynemo-runtime"
+version = "0.2.1"
+dependencies = [
+ "anyhow",
+ "async-nats",
+ "async-once-cell",
+ "async-stream",
+ "async-trait",
+ "async_zmq",
+ "blake3",
+ "bytes",
+ "chrono",
+ "derive-getters",
+ "derive_builder",
+ "educe",
+ "either",
+ "etcd-client",
+ "figment",
+ "futures",
+ "humantime",
+ "local-ip-address",
+ "log",
+ "nid",
+ "nix 0.29.0",
+ "nuid",
+ "once_cell",
+ "prometheus",
+ "rand",
+ "regex",
+ "serde",
+ "serde_json",
+ "socket2",
+ "thiserror 1.0.69",
+ "tokio",
+ "tokio-stream",
+ "tokio-util",
+ "tracing",
+ "tracing-subscriber",
+ "uuid 1.14.0",
+ "validator",
+ "xxhash-rust",
 ]
 
 [[package]]
@@ -5594,102 +5690,6 @@ dependencies = [
  "tracing-serde",
 ]
 
-[[package]]
-name = "triton-distributed-llm"
-version = "0.2.1"
-dependencies = [
- "anyhow",
- "async-openai",
- "async-stream",
- "async-trait",
- "async_zmq",
- "axum 0.8.1",
- "bindgen 0.70.1",
- "blake3",
- "bs62",
- "bytes",
- "chrono",
- "cmake",
- "derive_builder",
- "either",
- "erased-serde",
- "futures",
- "galil-seiferas",
- "indexmap 2.7.1",
- "itertools 0.14.0",
- "libc",
- "llama-cpp-2",
- "minijinja",
- "minijinja-contrib",
- "mistralrs",
- "prometheus",
- "pyo3",
- "regex",
- "semver",
- "serde",
- "serde-pickle",
- "serde_json",
- "serde_repr",
- "strum 0.27.1",
- "thiserror 2.0.11",
- "tokenizers",
- "tokio",
- "tokio-stream",
- "tokio-util",
- "toktrie 0.6.28",
- "toktrie_hf_tokenizers 0.6.28",
- "tracing",
- "triton-distributed-runtime",
- "unicode-segmentation",
- "uuid 1.14.0",
- "validator",
- "xxhash-rust",
-]
-
-[[package]]
-name = "triton-distributed-runtime"
-version = "0.2.1"
-dependencies = [
- "anyhow",
- "async-nats",
- "async-once-cell",
- "async-stream",
- "async-trait",
- "async_zmq",
- "blake3",
- "bytes",
- "chrono",
- "derive-getters",
- "derive_builder",
- "educe",
- "either",
- "etcd-client",
- "figment",
- "futures",
- "humantime",
- "local-ip-address",
- "log",
- "nid",
- "nix 0.29.0",
- "nuid",
- "once_cell",
- "prometheus",
- "rand",
- "regex",
- "serde",
- "serde_json",
- "socket2",
- "thiserror 1.0.69",
- "tokio",
- "tokio-stream",
- "tokio-util",
- "tracing",
- "tracing-subscriber",
- "uuid 1.14.0",
- "validator",
- "xxhash-rust",
-]
-
 [[package]]
 name = "try-lock"
 version = "0.2.5"

launch/dynemo-run/Cargo.toml

@@ -22,13 +22,13 @@ homepage = "https://github.com/dynemo-ai/dynemo"
 license = "Apache-2.0"
 
 [features]
-mistralrs = ["triton-distributed-llm/mistralrs"]
-sglang = ["triton-distributed-llm/sglang", "dep:netlink-packet-route", "dep:rtnetlink"]
-vllm = ["triton-distributed-llm/vllm", "dep:netlink-packet-route", "dep:rtnetlink"]
-llamacpp = ["triton-distributed-llm/llamacpp"]
-trtllm = ["triton-distributed-llm/trtllm"]
-cuda = ["triton-distributed-llm/cuda"]
-metal = ["triton-distributed-llm/metal"]
+mistralrs = ["dynemo-llm/mistralrs"]
+sglang = ["dynemo-llm/sglang", "dep:netlink-packet-route", "dep:rtnetlink"]
+vllm = ["dynemo-llm/vllm", "dep:netlink-packet-route", "dep:rtnetlink"]
+llamacpp = ["dynemo-llm/llamacpp"]
+trtllm = ["dynemo-llm/trtllm"]
+cuda = ["dynemo-llm/cuda"]
+metal = ["dynemo-llm/metal"]
 
 [dependencies]
 anyhow = "1"
@@ -48,5 +48,5 @@ tokio = { version = "1", features = ["full"] }
 tokio-util = { version = "0.7", features = ["codec", "net"] }
 tracing = { version = "0.1" }
 tracing-subscriber = { version = "0.3", features = ["env-filter", "local-time", "json"] }
-triton-distributed-runtime = { path = "../../lib/runtime" }
-triton-distributed-llm = { path = "../../lib/llm" }
+dynemo-runtime = { path = "../../lib/runtime" }
+dynemo-llm = { path = "../../lib/llm" }

launch/dynemo-run/src/input/endpoint.rs

@@ -13,7 +13,7 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use triton_distributed_llm::{
+use dynemo_llm::{
     backend::Backend,
     http::service::discovery::ModelEntry,
     model_type::ModelType,
@@ -25,10 +25,10 @@ use triton_distributed_llm::{
         Annotated,
     },
 };
-use triton_distributed_runtime::pipeline::{
+use dynemo_runtime::pipeline::{
     network::Ingress, ManyOut, Operator, SegmentSource, ServiceBackend, SingleIn, Source,
 };
-use triton_distributed_runtime::{protocols::Endpoint, DistributedRuntime, Runtime};
+use dynemo_runtime::{protocols::Endpoint, DistributedRuntime, Runtime};
 
 use crate::EngineConfig;
 

launch/dynemo-run/src/input/http.rs

@@ -15,7 +15,7 @@
 
 use std::sync::Arc;
 
-use triton_distributed_llm::{
+use dynemo_llm::{
     backend::Backend,
     http::service::{discovery, service_v2},
     model_type::ModelType,
@@ -27,7 +27,7 @@ use triton_distributed_llm::{
         Annotated,
     },
 };
-use triton_distributed_runtime::{
+use dynemo_runtime::{
     pipeline::{ManyOut, Operator, ServiceBackend, ServiceFrontend, SingleIn, Source},
     DistributedRuntime, Runtime,
 };