Merge branch 'main' into rmccormick/cp_anish_docs_to_main

Author: rmccorm4

.github/workflows/trigger_ci.yml

@@ -52,7 +52,7 @@ jobs:
             - 'components/backends/vllm/**'
             - 'tests/serve/test_vllm.py'
           trtllm:
-            - 'container/Dockerfile.tensorrt_llm'
+            - 'container/Dockerfile.trtllm'
             - 'components/backends/trtllm/**'
             - 'container/build.sh'
             - 'container/build_trtllm_wheel.sh'

components/backends/trtllm/src/dynamo/trtllm/main.py

@@ -229,9 +229,6 @@ async def init(runtime: DistributedRuntime, config: Config):
         endpoint = component.endpoint(config.endpoint)
 
         if is_first_worker(config):
-            # Get runtime configuration from the engine
-            runtime_config = await get_engine_runtime_config(engine, config)
-
             # Register the model with runtime config
             await register_llm(
                 modelType,
@@ -240,7 +237,6 @@ async def init(runtime: DistributedRuntime, config: Config):
                 config.served_model_name,
                 kv_cache_block_size=config.kv_block_size,
                 migration_limit=config.migration_limit,
-                runtime_config=runtime_config,  # Add runtime config here
             )
         # publisher will be set later if publishing is enabled.
         handler_config = RequestHandlerConfig(

components/backends/vllm/README.md

@@ -41,6 +41,7 @@ git checkout $(git describe --tags $(git rev-list --tags --max-count=1))
 | [**SLA-Based Planner**](../../../docs/architecture/sla_planner.md) | ✅ |  |
 | [**Load Based Planner**](../../../docs/architecture/load_planner.md) | 🚧 | WIP |
 | [**KVBM**](../../../docs/architecture/kvbm_architecture.md) | 🚧 | WIP |
+| [**LMCache**](./LMCache_Integration.md) | ✅ |  |
 
 ### Large Scale P/D and WideEP Features
 

components/backends/vllm/src/dynamo/vllm/main.py

@@ -132,7 +132,6 @@ async def init_prefill(runtime: DistributedRuntime, config: Config):
     """
     Instantiate and serve
     """
-
     component = runtime.namespace(config.namespace).component(config.component)
     await component.create_service()