-
Notifications
You must be signed in to change notification settings - Fork 3k
All issues
Issue creation is restricted in this repository
Issues
is:issue state:open
is:issue state:open
Search results
Hermes Portable uninstall cannot retire schema-5 inference authority
area: installInstall, setup, prerequisites, or uninstall flowInstall, setup, prerequisites, or uninstall flowarea: local-modelsLocal model providers, downloads, launch, or connectivityLocal model providers, downloads, launch, or connectivityintegration: hermesHermes integration behaviorHermes integration behaviorplatform: containerAffects Docker, containerd, Podman, or imagesAffects Docker, containerd, Podman, or imagesprovider: ollamaOllama local model provider behaviorOllama local model provider behaviorv0.0.111Release targetRelease targetStatus: Open.#9608 In NVIDIA/NemoClaw;nemoclaw connect re-establishes the dashboard forward but never completes or proves background handoff
area: cliCommand line interface, flags, terminal UX, or outputCommand line interface, flags, terminal UX, or outputarea: e2eEnd-to-end tests, nightly failures, or validation infrastructureEnd-to-end tests, nightly failures, or validation infrastructurearea: sandboxOpenShell sandbox lifecycle, runtime, config, or recoveryOpenShell sandbox lifecycle, runtime, config, or recoveryStatus: Open.#9606 In NVIDIA/NemoClaw;[WSL2][Onboard] nemoclaw onboard hangs indefinitely at "Configuring inference provider" when the Windows-host Ollama port check is slow
needs: triageAwaiting maintainer classificationAwaiting maintainer classificationNV QABugs found by the NVIDIA QA TeamBugs found by the NVIDIA QA TeamStatus: Open.[Linux][Onboard] nemoclaw onboard with NEMOCLAW_PROVIDER=llama-cpp always fails with 'conflicting or incomplete native llama.cpp evidence' on all released llama-server builds
needs: triageAwaiting maintainer classificationAwaiting maintainer classificationNV QABugs found by the NVIDIA QA TeamBugs found by the NVIDIA QA TeamUATIssues flagged for User Acceptance Testing.Issues flagged for User Acceptance Testing.Status: Open.[DGX Spark][Onboard] profile onboard reuses existing running vLLM instead of starting profile-specified muse-glimmer model
needs: triageAwaiting maintainer classificationAwaiting maintainer classificationNV QABugs found by the NVIDIA QA TeamBugs found by the NVIDIA QA TeamStatus: Open.[DGX Spark][Inference] vLLM container missing sentencepiece/tiktoken — Muse Glimmer 30B NVFP4 W4A4 tokenizer initialization fails at startup
needs: triageAwaiting maintainer classificationAwaiting maintainer classificationNV QABugs found by the NVIDIA QA TeamBugs found by the NVIDIA QA TeamUATIssues flagged for User Acceptance Testing.Issues flagged for User Acceptance Testing.Status: Open.- Status: Open.#9600 In NVIDIA/NemoClaw;
- Status: Open.#9599 In NVIDIA/NemoClaw;
- Status: Open.#9598 In NVIDIA/NemoClaw;
Portable onboarding reaches host Ollama before the Podman runner exists
area: local-modelsLocal model providers, downloads, launch, or connectivityLocal model providers, downloads, launch, or connectivityarea: onboardingOnboarding FSM, provider setup, sandbox launch, or first-run flowOnboarding FSM, provider setup, sandbox launch, or first-run flowintegration: hermesHermes integration behaviorHermes integration behaviorplatform: containerAffects Docker, containerd, Podman, or imagesAffects Docker, containerd, Podman, or imagesprovider: ollamaOllama local model provider behaviorOllama local model provider behaviorv0.0.111Release targetRelease targetStatus: Open.#9596 In NVIDIA/NemoClaw;[macOS][CLI&UX] status reports "Inference (upstream): unauthorized (HTTP 401)" while the managed inference route works
needs: triageAwaiting maintainer classificationAwaiting maintainer classificationNV QABugs found by the NVIDIA QA TeamBugs found by the NVIDIA QA TeamStatus: Open.[Ubuntu 26.04][Onboard] onboard reuses a running managed gateway without recreating a missing openshell-docker network — sandbox creation fails (Docker 404)
needs: triageAwaiting maintainer classificationAwaiting maintainer classificationNV QABugs found by the NVIDIA QA TeamBugs found by the NVIDIA QA TeamStatus: Open.