-
Notifications
You must be signed in to change notification settings - Fork 372
Pull requests: lemonade-sdk/lemonade
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Fix startup self-deadlock with a thread-local recursion guard (minimal alt to #2443)
bug
Something isn't working
cpp
runtime::rocm
AMD ROCm runtime
Fix three broken doc links found by zensical
documentation
Improvements or additions to documentation
Fix flaky Ollama tool-calling CI by disabling default thinking for tool requests
area::api
HTTP REST API surface and route handlers
bug
Something isn't working
fix(packaging): strip lemonade-tray from RPM
area::installer
Windows MSI / macOS DMG / Debian / RPM packaging
enhancement
New feature or request
#2484
opened Jun 29, 2026 by
lucifer-vali
Collaborator
Loading…
[Router] 2381 unified interface for semantic_similarity and model classifier
enhancement
New feature or request
#2483
opened Jun 29, 2026 by
SlawomirNowaczyk
Collaborator
Loading…
[Router] 2381 semantic_similarity classifier (M5)
cpp
enhancement
New feature or request
#2482
opened Jun 29, 2026 by
SlawomirNowaczyk
Collaborator
Loading…
fix(whisper): convert non-WAV audio to WAV for Open WebUI compatibility
bug
Something isn't working
engine::whispercpp
whisper.cpp backend; audio transcription
fix(auto-label): refactor community user checks to exclude bots
enhancement
New feature or request
#2479
opened Jun 29, 2026 by
fl0rianr
Collaborator
Loading…
Update stable-diffusion.cpp to master-721-8caa3f9 and CUDA master-726-db48014
#2477
opened Jun 28, 2026 by
github-actions
Bot
Loading…
fix: hide NVIDIA GPUs from vLLM on dual-GPU systems (#1863)
bug
Something isn't working
engine::vllm
vLLM backend (experimental, ROCm Linux, Strix Halo)
priority::😎warm
runtime::rocm
AMD ROCm runtime
#2474
opened Jun 28, 2026 by
bong-water-water-bong
Contributor
Loading…
docs: add Fedora 43 to FLM NPU Linux setup guide
documentation
Improvements or additions to documentation
#2473
opened Jun 28, 2026 by
bong-water-water-bong
Contributor
Loading…
Add lemon-mlx-engine as a wrapped-server backend (rebase of #2010)
enhancement
New feature or request
#2472
opened Jun 28, 2026 by
bong-water-water-bong
Contributor
Loading…
ci: publish rolling edge and sha-* Docker images on main push (#2372)
area::ci
CI / GitHub Actions / self-hosted runner infrastructure
#2470
opened Jun 27, 2026 by
bong-water-water-bong
Contributor
Loading…
docs: document draft checkpoint key and add MTP model example (#2435)
documentation
Improvements or additions to documentation
#2469
opened Jun 27, 2026 by
bong-water-water-bong
Contributor
Loading…
fix: show warning when pulling model in offline mode (#2412)
bug
Something isn't working
#2468
opened Jun 27, 2026 by
bong-water-water-bong
Contributor
Loading…
fix: skip redundant TheRock download when already installed (#2413)
bug
Something isn't working
engine::llamacpp
llama.cpp backend (LlamaCppServer); GPU/CPU LLM inference (Vulkan, ROCm, Metal)
runtime::rocm
AMD ROCm runtime
#2467
opened Jun 27, 2026 by
bong-water-water-bong
Contributor
Loading…
feat: add setup-repo-secrets script and document required PR-Agent secrets
area::ci
CI / GitHub Actions / self-hosted runner infrastructure
documentation
Improvements or additions to documentation
#2466
opened Jun 27, 2026 by
bong-water-water-bong
Contributor
Loading…
fix: skip optional draft checkpoint in are_required_checkpoints_complete (#2435)
bug
Something isn't working
#2465
opened Jun 27, 2026 by
bong-water-water-bong
Contributor
Loading…
fix: enable --fit, make --no-mmproj-offload overridable, add -ngl (#1848 #2358 #2215)
engine::llamacpp
llama.cpp backend (LlamaCppServer); GPU/CPU LLM inference (Vulkan, ROCm, Metal)
enhancement
New feature or request
#2464
opened Jun 27, 2026 by
bong-water-water-bong
Contributor
Loading…
fix: omni size filtering, .completed sentinel backfill, disk space pre-check (#2201 #1341 #1999 #1003)
bug
Something isn't working
cpp
#2463
opened Jun 27, 2026 by
bong-water-water-bong
Contributor
Loading…
fix: cancel model download on Ctrl+C (SIGINT) via libcurl progress callback (#1385)
bug
Something isn't working
#2462
opened Jun 27, 2026 by
bong-water-water-bong
Contributor
Loading…
fix: add gfx1152 (Krackan APU) to whispercpp:rocm and vllm:rocm (#2002)
bug
Something isn't working
engine::whispercpp
whisper.cpp backend; audio transcription
priority::😎warm
runtime::rocm
AMD ROCm runtime
#2461
opened Jun 27, 2026 by
bong-water-water-bong
Contributor
Loading…
fix: pre-flight GPU device check for ROCm llama-server backends (#1787)
engine::llamacpp
llama.cpp backend (LlamaCppServer); GPU/CPU LLM inference (Vulkan, ROCm, Metal)
enhancement
New feature or request
runtime::rocm
AMD ROCm runtime
#2460
opened Jun 27, 2026 by
bong-water-water-bong
Contributor
Loading…
fix: pick best AMD GPU (dGPU > iGPU) in get_rocm_arch() instead of first available
bug
Something isn't working
engine::ryzenai
RyzenAI hybrid NPU backend
priority::😎warm
runtime::rocm
AMD ROCm runtime
#2459
opened Jun 27, 2026 by
bong-water-water-bong
Contributor
Loading…
fix: skip MTP speculative decoding when no mmproj available (#2451)
bug
Something isn't working
engine::llamacpp
llama.cpp backend (LlamaCppServer); GPU/CPU LLM inference (Vulkan, ROCm, Metal)
#2458
opened Jun 27, 2026 by
bong-water-water-bong
Contributor
Loading…
Previous Next
ProTip!
Mix and match filters to narrow down what you’re looking for.