valknar

0 Followers · 0 Following

• Joined on 2025-11-15

Repositories

27

Projects Packages Public Activity Starred Repositories

valknar pushed to main at valknar/docker-compose 2025-11-21 18:57:13 +01:00

81d4058c5d revert: back to openai prefix for vLLM OpenAI-compatible endpoint

valknar pushed to main at valknar/docker-compose 2025-11-21 18:54:50 +01:00

4a575bc0da fix: use hosted_vllm prefix instead of openai for vLLM streaming compatibility

valknar pushed to main at valknar/docker-compose 2025-11-21 18:46:44 +01:00

01a345979b fix: disable drop_params to preserve streaming metadata in LiteLLM

valknar pushed to main at valknar/docker-compose 2025-11-21 18:42:49 +01:00

c58b5d36ba revert: remove direct WebUI connection, focus on fixing LiteLLM streaming

valknar pushed to main at valknar/docker-compose 2025-11-21 18:38:42 +01:00

62fcf832da feat: add direct RunPod orchestrator connection to WebUI for streaming bypass

valknar pushed to main at valknar/paint-ui 2025-11-21 18:31:31 +01:00

54aac626a2 feat: add Import Image functionality to add images as new layers

valknar pushed to main at valknar/runpod 2025-11-21 18:25:53 +01:00

7f1890517d fix: enable eager execution for proper token streaming in vLLM

valknar pushed to main at valknar/runpod 2025-11-21 18:10:56 +01:00

94080da341 fix: remove incorrect start-vllm.sh that would break orchestrator architecture

valknar pushed to main at valknar/runpod 2025-11-21 18:08:23 +01:00

6944e4ebd5 feat: add vllm serve script with proper streaming support

valknar pushed to main at valknar/docker-compose 2025-11-21 18:01:03 +01:00

dfde1df72f fix: add /v1 suffix to vLLM api_base for proper endpoint routing

valknar pushed to main at valknar/docker-compose 2025-11-21 17:55:12 +01:00

42a68bc0b5 fix: revert to openai prefix, remove /v1 suffix from api_base

valknar pushed to main at valknar/paint-ui 2025-11-21 17:54:01 +01:00

6a47efc164 fix: resolve TypeScript errors in mini-map and layer-effects-panel

valknar pushed to main at valknar/docker-compose 2025-11-21 17:52:36 +01:00

699c8537b0 fix: use LiteLLM vLLM pass-through for qwen model

valknar pushed to main at valknar/paint-ui 2025-11-21 17:51:43 +01:00

5c4763cb62 feat(phase-12): add professional UI polish with status bar, navigator, and shortcuts help

valknar pushed to main at valknar/docker-compose 2025-11-21 17:43:37 +01:00

ed4d537499 Enable verbose logging in LiteLLM for streaming debug

valknar pushed to main at valknar/paint-ui 2025-11-21 17:42:46 +01:00

9aa6e2d5d9 feat(phase-11): implement comprehensive non-destructive layer effects system

valknar pushed to main at valknar/runpod 2025-11-21 17:23:35 +01:00

d21caa56bc fix: implement incremental streaming deltas for vLLM chat completions

valknar pushed to main at valknar/paint-ui 2025-11-21 17:16:15 +01:00

63a6801155 feat: implement comprehensive canvas context menu system

valknar pushed to main at valknar/docker-compose 2025-11-21 17:13:52 +01:00

103bbbad51 debug: enable INFO logging in LiteLLM for troubleshooting

valknar pushed to main at valknar/docker-compose 2025-11-21 17:06:03 +01:00

92a7436716 fix(ai): add 600s timeout for qwen model requests via Tailscale