tt-inference-server

Blaze image should not contain raw code

#2836 · Apr 8, 2026

Medium

Shield Inference technologies cpp-server

Investigate ffmpeg + hardware acceleration

#2826 · Apr 8, 2026

Medium

Shield Inference technologies cpp-server

Investigate usage of GuideLLM for multi-turn conversation & coding agent benchmarking

#2824 · Apr 8, 2026

Medium

perf_benchmarks P1 performance testing

Re-validate fixes LLM and VLM models that were previously incapable of being released

#2823 · Apr 8, 2026

Medium

model_readiness_release model_readiness_support

Determine which ModelSpecs are incapable/capable of being released

#2822 · Apr 8, 2026

Medium

model_readiness_release model_readiness_support

Identify and enumerate which ModelSpecs are using the old Docker interface

#2821 · Apr 8, 2026

Medium

model_readiness_release model_readiness_support

fix: report scoring fails for evals using multilevel result_keys (whisper, math leaderboard)

#2819 · Apr 8, 2026

Medium

Uplift all LLM and VLM ModelSpecs to use new Docker interface

#2818 · Apr 8, 2026

Medium

model_readiness_release P0 model_readiness_support

Consolidate Whisper and SpeechT5 ModelSpecTemplates

#2817 · Apr 8, 2026

Medium

good first issue Tech Debt

Performance Regress for Qwen VL 7B 0.8.0 vs Current Dev

#2815 · Apr 7, 2026

Medium

Add max number of sessions

#2806 · Apr 7, 2026

Medium

Shield Inference technologies cpp-server

Figure out how to do C++ deployment without blaze

#2804 · Apr 7, 2026

Medium

invalid Shield Inference technologies cpp-server

Improve embedding models task assignment to get 100% utilization per runner

#2803 · Apr 7, 2026

Medium

Shield Inference technologies cpp-server

[Helm] Enforce 1:1 Pod:Node allocation

#2801 · Apr 7, 2026

Medium

P0 Helm

[Helm] Automated Documentation & CI Merge Gates

#2800 · Apr 7, 2026

Medium

P0 Helm

[Helm] Automatic configuration of host resource requests

#2799 · Apr 7, 2026

Medium

P0 Helm

[Helm] Automatic configuration of probe timing

#2798 · Apr 7, 2026

Medium

P0 Helm

[Helm] Enable model specification select at helm install time

#2797 · Apr 7, 2026

Medium

P0 Helm

Rewrite session manager scaling

#2793 · Apr 6, 2026

Medium

Shield Inference technologies cpp-server

[Helm] Automated values.yaml Catalogue Generation

#2786 · Apr 6, 2026

Medium

P0 Helm

[Helm] Implement core template trinity

#2784 · Apr 6, 2026

Medium

P0 Helm

[Helm] v0.1.0 Helm Chart

#2782 · Apr 6, 2026

Medium

enhancement P0 Helm

Try to optimize performance for embedding models

#2779 · Apr 6, 2026

Medium

Shield Inference technologies cpp-server

Fix worker telemetry for media server

#2764 · Apr 4, 2026

Medium

Shield Inference technologies

Warmup issues

#2753 · Apr 3, 2026

Medium

Shield Inference technologies cpp-server

Gaps in unit test coverage

#2746 · Apr 3, 2026

Medium

Shield Inference technologies Tech Debt cpp-server

Add C++ code coverage measurement in CI

#2744 · Apr 3, 2026

Medium

Shield Inference technologies Tech Debt cpp-server

Fix documentation issues in README and CLAUDE.md

#2741 · Apr 3, 2026

Medium

Shield Inference technologies Tech Debt cpp-server

Remove video creation from the main flow

#2739 · Apr 3, 2026

Medium

Shield Inference technologies

Getting the same slot multiple times

#2737 · Apr 3, 2026

Medium

Shield Inference technologies cpp-server

Support request cancellation (slot release) in SP runner

#2732 · Apr 3, 2026

Medium

Shield Inference technologies cpp-server

Improve error handling

#2730 · Apr 3, 2026

Medium

Shield Inference technologies cpp-server

Beginner-Friendly Issues 32