-
Notifications
You must be signed in to change notification settings - Fork 463
All issues
Issue creation is restricted in this repository
Issues
is:issue state:open
is:issue state:open
Search results
/v1/modelsresponse missingcontext_length— OpenAI-compatible clients cannot determine effective runtime contextarea::apiHTTP REST API surface and route handlersHTTP REST API surface and route handlersenhancementNew feature or requestNew feature or requestStatus: Open.#3046 In lemonade-sdk/lemonade;Refine the chat tab copy button next to the model name
enhancementNew feature or requestNew feature or requestStatus: Open.Perf regression: llamacpp-amd-ecosystem-gfx11, llamacpp-rocm-nightly
performancePerformancePerformanceregressionPerformance regressionPerformance regressionStatus: Open.#3044 In lemonade-sdk/lemonade;Update all the graphical assets that show GUI2
documentationImprovements or additions to documentationImprovements or additions to documentationStatus: Open.Perf regression: llamacpp-amd-ecosystem-gfx11
performancePerformancePerformanceregressionPerformance regressionPerformance regressionStatus: Open.#3040 In lemonade-sdk/lemonade;Loading GUI3 takes ~10 seconds
enhancementNew feature or requestNew feature or requestStatus: Open.- Status: Open.#3027 In lemonade-sdk/lemonade;
Systray icon keeps disappearing
area::traySystem tray app (LemonadeServer.exe, lemonade-tray)System tray app (LemonadeServer.exe, lemonade-tray)bugSomething isn't workingSomething isn't workingStatus: Open.#3025 In lemonade-sdk/lemonade;Test: Wire exiting stale tests into the CI suite
area::ciCI / GitHub Actions / self-hosted runner infrastructureCI / GitHub Actions / self-hosted runner infrastructureenhancementNew feature or requestNew feature or requestStatus: Open.#3019 In lemonade-sdk/lemonade;CUDA context auto-tuning uses AMD GPU memory on a hybrid AMD/NVIDIA system
bugSomething isn't workingSomething isn't workingengine::llamacppllama.cpp backend (LlamaCppServer); GPU/CPU LLM inference (Vulkan, ROCm, Metal)llama.cpp backend (LlamaCppServer); GPU/CPU LLM inference (Vulkan, ROCm, Metal)runtime::cudaNVIDIA CUDA runtimeNVIDIA CUDA runtimeStatus: Open.#3017 In lemonade-sdk/lemonade;test/server_eviction.py never runs in CI, and /internal/simulate-vram-pressure exists only to serve it
area::ciCI / GitHub Actions / self-hosted runner infrastructureCI / GitHub Actions / self-hosted runner infrastructureenhancementNew feature or requestNew feature or requestStatus: Open.#3010 In lemonade-sdk/lemonade;- Status: Open.