-
Notifications
You must be signed in to change notification settings - Fork 1.3k
All issues
Issue creation is restricted in this repository
Issues
is:issue state:open
is:issue state:open
Search results
ai-dynamo frontend TCP accept-loop exhausts file descriptors and enters a runaway, unbounded retry loop under high concurrency, instead of backing off
backend::vllmRelates to the vllm backendRelates to the vllm backendbugSomething isn't workingSomething isn't workingdynamo-runtimeRelates to the dynamo-runtime componentRelates to the dynamo-runtime componentfrontend`python -m dynamo.frontend` and `dynamo-run in=http|text|grpc``python -m dynamo.frontend` and `dynamo-run in=http|text|grpc`language::rustIssues/PRs that reference Rust codeIssues/PRs that reference Rust codeobservabilityRelated to metrics, tracing, loggingRelated to metrics, tracing, loggingperformanceInvolves the performance of DynamoInvolves the performance of DynamoStatus: Open.#11801 In ai-dynamo/dynamo;[BUG]: ai-dynamo/vllm-runtime:1.3.0-dev.1-cuda13 ships a self-inconsistent nvidia_cutlass_dsl (missing
increment_coord) —import cutlassfailsbackend::vllmRelates to the vllm backendRelates to the vllm backendbugSomething isn't workingSomething isn't workingdynamo-runtimeRelates to the dynamo-runtime componentRelates to the dynamo-runtime componentStatus: Open.#11775 In ai-dynamo/dynamo;DEP (light): Experimental replicaGrouping for single-node Grove components
deployment::k8sRelates to dynamo deployment in kubernetesRelates to dynamo deployment in kubernetesdynamo-deployRelates to dynamo-deploy binaryRelates to dynamo-deploy binaryStatus: Open.#11774 In ai-dynamo/dynamo;feat(request-trace): native S3 sink for request-trace records
dynamo-llmRelates to dynamo-llm componentRelates to dynamo-llm componentlanguage::rustIssues/PRs that reference Rust codeIssues/PRs that reference Rust codeobservabilityRelated to metrics, tracing, loggingRelated to metrics, tracing, loggingStatus: Open.#11768 In ai-dynamo/dynamo;[BUG]: /v1/messages returns 500 for Claude Code ≥2.1.154 — mid-conversation
role:"system"turns fail chat-template renderingbackend::vllmRelates to the vllm backendRelates to the vllm backendbugSomething isn't workingSomething isn't workingfrontend`python -m dynamo.frontend` and `dynamo-run in=http|text|grpc``python -m dynamo.frontend` and `dynamo-run in=http|text|grpc`language::rustIssues/PRs that reference Rust codeIssues/PRs that reference Rust codeStatus: Open.#11762 In ai-dynamo/dynamo;[BUG]: vllm-runtime 1.2.x pins vLLM 0.20.1, which has a CUDA illegal-memory-access regression for gpt-oss (MXFP4) at long contexts — please bump or backport
backend::vllmRelates to the vllm backendRelates to the vllm backendbugSomething isn't workingSomething isn't workingdependenciesRelates to dependencies of DynamoRelates to dependencies of Dynamodynamo-runtimeRelates to the dynamo-runtime componentRelates to the dynamo-runtime componentStatus: Open.#11761 In ai-dynamo/dynamo;[FEATURE]: Model vLLM hybrid KV cache groups in mocker replays
backend::vllmRelates to the vllm backendRelates to the vllm backendbugSomething isn't workingSomething isn't workingdynamo-llmRelates to dynamo-llm componentRelates to dynamo-llm componentenhancementNew feature or requestNew feature or requestlanguage::rustIssues/PRs that reference Rust codeIssues/PRs that reference Rust codeStatus: Open.#11726 In ai-dynamo/dynamo;[BUG]: Compliance check fails for vLLM CPU images
backend::vllmRelates to the vllm backendRelates to the vllm backendbugSomething isn't workingSomething isn't workingStatus: Open.#11706 In ai-dynamo/dynamo;[BUG]: vLLM chat-processor ignores --default-chat-template-kwargs
backend::vllmRelates to the vllm backendRelates to the vllm backendbugSomething isn't workingSomething isn't workingfrontend`python -m dynamo.frontend` and `dynamo-run in=http|text|grpc``python -m dynamo.frontend` and `dynamo-run in=http|text|grpc`language::pythonIssues/PRs that reference Python codeIssues/PRs that reference Python codeStatus: Open.#11703 In ai-dynamo/dynamo;DEP: KV Cache Controller
dep:draftDEP in draft statusDEP in draft statusenhancementNew feature or requestNew feature or requestrouterRelates to routing, KV-aware routing, etc.Relates to routing, KV-aware routing, etc.Status: Open.DEP: EPP Embedded SelectionService Interface
backend::sglangRelates to the sglang backendRelates to the sglang backendbackend::trtllmRelates to the trtllm backendRelates to the trtllm backendbackend::vllmRelates to the vllm backendRelates to the vllm backenddep:draftDEP in draft statusDEP in draft statusdeployment::k8sRelates to dynamo deployment in kubernetesRelates to dynamo deployment in kubernetesenhancementNew feature or requestNew feature or requestrouterRelates to routing, KV-aware routing, etc.Relates to routing, KV-aware routing, etc.Status: Open.#11661 In ai-dynamo/dynamo;[DOCS]: Fix incorrect default maximum for request duration histogram
bugSomething isn't workingSomething isn't workingdocumentationImprovements or additions to documentationImprovements or additions to documentationlanguage::rustIssues/PRs that reference Rust codeIssues/PRs that reference Rust codeobservabilityRelated to metrics, tracing, loggingRelated to metrics, tracing, loggingStatus: Open.#11657 In ai-dynamo/dynamo;