Arthur Erlich

haylan commented on pull request haylan/git-contribution-graph#29

2026-09-09 22:05:24 +00:00

chore(deps): update dependency monolog/monolog to v3.12.0

/review

haylan pushed to main at haylan/LLM-Server

2026-09-09 17:10:45 +00:00

930e407053 docs(llm): document qwen-classifier reality, add --reasoning off safety net

haylan pushed to main at haylan/LLM-Server

2026-09-09 16:10:51 +00:00

76043e2c6f tune(llm): partial GPU offload for qwen-classifier, real headroom

haylan pushed to main at haylan/LLM-Server

2026-09-09 15:04:19 +00:00

1102273384 fix(llm): enable flash-attn on qwen-classifier, real VRAM cause found

haylan pushed to main at haylan/LLM-Server

2026-09-09 15:03:12 +00:00

ba9ace6f71 fix(llm): shrink qwen-classifier's compute buffer for real VRAM headroom

haylan pushed to main at haylan/LLM-Server

2026-09-09 14:59:14 +00:00

8e2650807c fix(llm): move qwen-classifier to GPU, right-size context

haylan pushed to main at haylan/LLM-Server

2026-09-09 14:38:23 +00:00

4353e5c0e8 merge: follow-up fix for qwen-classifier model file

20cc0bcc70 fix(llm): point qwen-classifier at the Q8 GGUF already on disk

Compare 2 commits »

haylan pushed to fix/omniroute-pr-agent-timeout at haylan/LLM-Server

2026-09-09 14:38:08 +00:00

20cc0bcc70 fix(llm): point qwen-classifier at the Q8 GGUF already on disk

haylan pushed to main at haylan/LLM-Server

2026-09-09 14:29:14 +00:00

c1e30ec9bb Merge pull request 'Fix/omniroute pr agent timeout' (#54) from fix/omniroute-pr-agent-timeout into main

b3a64fe4b5 chroe(chore): added markdown for harnesses

828bd4c046 feat(llm): dedicate a CPU-only backend for the qwen-code tool-call classifier

Compare 3 commits »

haylan merged pull request haylan/LLM-Server#54

2026-09-09 14:29:13 +00:00

Fix/omniroute pr agent timeout

haylan created pull request haylan/LLM-Server#54

2026-09-09 14:29:06 +00:00

Fix/omniroute pr agent timeout

haylan pushed to fix/omniroute-pr-agent-timeout at haylan/LLM-Server

2026-09-09 14:28:55 +00:00

b3a64fe4b5 chroe(chore): added markdown for harnesses

haylan pushed to fix/omniroute-pr-agent-timeout at haylan/LLM-Server

2026-09-09 14:27:16 +00:00

828bd4c046 feat(llm): dedicate a CPU-only backend for the qwen-code tool-call classifier

haylan created branch fix/omniroute-pr-agent-timeout in haylan/LLM-Server

2026-09-09 14:27:16 +00:00

haylan pushed to main at haylan/LLM-Server

2026-09-09 06:22:36 +00:00

16df051318 docs(research): add ponytail audit report highlighting over-engineering and complexity issues

haylan pushed to main at haylan/LLM-Server

2026-09-09 05:32:14 +00:00

128503b68a docs: add AGENTS.md and QWEN.md with agent instructions and project overview

haylan pushed to main at haylan/LLM-Server

2026-09-08 10:46:54 +00:00

df900404c0 chore(config): fix ignored path .qwen/temp to .qwen/tmp

f4729ba704 docs(research): evaluate Colibrì for this stack

Compare 2 commits »

haylan pushed to main at haylan/LLM-Server

2026-09-08 10:30:40 +00:00

8f3feb4881 Merge branch 'feat-rag-databases'

6f4e736da8 docs(coding-cli-setup): split per-CLI docs into their own files

Compare 2 commits »

haylan created branch feat-rag-databases in haylan/LLM-Server

2026-09-08 10:30:21 +00:00

haylan pushed to feat-rag-databases at haylan/LLM-Server

2026-09-08 10:30:21 +00:00

6f4e736da8 docs(coding-cli-setup): split per-CLI docs into their own files