-
Notifications
You must be signed in to change notification settings - Fork 372
Issues
is:issue state:open
is:issue state:open
Issue creation is restricted in this repository
Search results
Unstable on Ubuntu 25.10??
bugSomething isn't workingSomething isn't workingengine::flmFastFlowLM backend (NPU); multi-modal LLM/ASR/embeddings/rerankingFastFlowLM backend (NPU); multi-modal LLM/ASR/embeddings/rerankingruntime::rocmAMD ROCm runtimeAMD ROCm runtimeStatus: Open.#2494 In lemonade-sdk/lemonade;HTTP error 404 for llama-b9752-windows-cuda-sm_89-x64.7z
area::traySystem tray app (LemonadeServer.exe, lemonade-tray)System tray app (LemonadeServer.exe, lemonade-tray)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.#2492 In lemonade-sdk/lemonade;- Status: Open.#2487 In lemonade-sdk/lemonade;
[feature request] auto-extract model family from GGUF and automatically apply recommended params. huge UX improvement!
enhancementNew feature or requestNew feature or requestStatus: Open.#2480 In lemonade-sdk/lemonade;Qwen3.6-27B-MTP-GGUF Support
bugSomething isn't workingSomething isn't workingStatus: Open.#2478 In lemonade-sdk/lemonade;[BUG] 99% GPU (ROCm) idle usage when both LLM and Embedding models are loaded simultaneously
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::rocmAMD ROCm runtimeAMD ROCm runtimeStatus: Open.#2475 In lemonade-sdk/lemonade;[Testing] lemonade-cachy-build
area::ciCI / GitHub Actions / self-hosted runner infrastructureCI / GitHub Actions / self-hosted runner infrastructureengine::llamacppllama.cpp backend (LlamaCppServer); GPU/CPU LLM inference (Vulkan, ROCm, Metal)llama.cpp backend (LlamaCppServer); GPU/CPU LLM inference (Vulkan, ROCm, Metal)enhancementNew feature or requestNew feature or requestruntime::rocmAMD ROCm runtimeAMD ROCm runtimeStatus: Open.#2471 In lemonade-sdk/lemonade;GLM-4.5-Air-UD-Q4K-XL-GGUF failing on Strix Halo
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::rocmAMD ROCm runtimeAMD ROCm runtimeStatus: Open.#2451 In lemonade-sdk/lemonade;Respect github API rate limits
bugSomething isn't workingSomething isn't workingStatus: Open.#2441 In lemonade-sdk/lemonade;a11y: remove preset rails for backends and enable a global but merged solution
enhancementNew feature or requestNew feature or requestsquadSquad triage inbox — Lead will assign to a memberSquad triage inbox — Lead will assign to a membersquad:mattinglyAssigned to ⚛️ Mattingly (UI / Frontend)Assigned to ⚛️ Mattingly (UI / Frontend)Status: Open.GUI3: master-detail model view — Slice 2 (Files tab, real storage stats, polish)
enhancementNew feature or requestNew feature or requestsquadSquad triage inbox — Lead will assign to a memberSquad triage inbox — Lead will assign to a membersquad:mattinglyAssigned to ⚛️ Mattingly (UI / Frontend)Assigned to ⚛️ Mattingly (UI / Frontend)Status: Open.[Router] Back-compat conformance corpus (golden policy → Decision tests)
area::ciCI / GitHub Actions / self-hosted runner infrastructureCI / GitHub Actions / self-hosted runner infrastructureenhancementNew feature or requestNew feature or requestStatus: Open.