valknar

0 Followers · 0 Following

• Joined on 2025-11-15

Repositories

26

Projects Packages Public Activity Starred Repositories

valknar pushed to main at valknar/pivoine.art 2025-12-03 14:37:40 +01:00

valknar pushed to main at valknar/pivoine.art 2025-12-03 14:37:35 +01:00

valknar pushed to main at valknar/pivoine.art 2025-12-03 14:37:32 +01:00

valknar pushed to main at valknar/pivoine.art 2025-12-03 14:37:25 +01:00

valknar pushed to main at valknar/pivoine.art 2025-12-03 14:37:19 +01:00

edd0083c99 Last Sync: 2025-12-03 14:37 (Mobile)

valknar pushed to main at valknar/.llmx 2025-12-01 06:27:17 +01:00

5eda3b5c6a refactor: clean up config, switch to claude-sonnet-4-5

valknar pushed to main at valknar/.llmx 2025-12-01 04:58:54 +01:00

4292a2d62c feat: add Brave Search MCP, disable unused MCP servers

valknar pushed tag rust-v0.1.9 to valknar/llmx 2025-12-01 00:04:07 +01:00

valknar pushed to main at valknar/llmx 2025-12-01 00:04:06 +01:00

66e0649b01 chore: Bump version to 0.1.9

valknar pushed to main at valknar/runpod-ai-orchestrator 2025-11-30 22:46:36 +01:00

f8694653d0 fix: adjust VRAM for 24K context based on actual usage

valknar pushed to main at valknar/runpod-ai-orchestrator 2025-11-30 22:39:11 +01:00

078043e35a feat: balance Llama 24K context with concurrent BGE

valknar pushed to main at valknar/runpod-ai-orchestrator 2025-11-30 22:37:13 +01:00

c969d10eaf feat: increase Llama context to 32K with 95% VRAM

valknar pushed to main at valknar/runpod-ai-orchestrator 2025-11-30 22:15:15 +01:00

f68bc47915 feat: increase Llama max-model-len to 20480

valknar pushed to main at valknar/.llmx 2025-11-30 21:58:23 +01:00

b1817230c6 fix: redirect print() to stderr for stdio MCP transport

valknar pushed to main at valknar/.llmx 2025-11-30 21:44:12 +01:00

45624a4d91 fix: switch MCP server to stdio transport for llmx compatibility

valknar pushed to main at valknar/.llmx 2025-11-30 21:36:38 +01:00

6724fea494 perf: optimize Docker build time from >10min to ~2min

valknar pushed to main at valknar/runpod-ai-orchestrator 2025-11-30 20:16:02 +01:00

b2de3b17ee fix: adjust VRAM allocation for concurrent Llama+BGE

valknar pushed to main at valknar/runpod-ai-orchestrator 2025-11-30 19:55:19 +01:00

f668e06228 feat: add BGE embedding model for concurrent operation with Llama

valknar pushed to main at valknar/pivoine.art 2025-11-30 16:20:15 +01:00

dadd59d3f5 feat(tracks): bunker

valknar pushed to main at valknar/pivoine.art 2025-11-30 16:17:08 +01:00

646c002741 feat(tracks): bunker