Arthur Erlich

haylan closed issue haylan/LLM-Server#7

2026-08-24 16:17:37 +00:00

Research OpenCode CLI installation and local-endpoint setup

haylan commented on issue haylan/LLM-Server#7

2026-08-24 16:17:31 +00:00

Research OpenCode CLI installation and local-endpoint setup

Resolved. Full findings: docs/research/opencode-cli-setup.md on branch research/opencode-cli-setup.

Project confirmed: sst/opencode moved orgs — now github.com/anomalyco/opencode…

haylan opened issue haylan/LLM-Server#7

2026-08-24 16:13:20 +00:00

Research OpenCode CLI installation and local-endpoint setup

haylan pushed to main at haylan/LLM-Server

2026-08-24 16:10:05 +00:00

408a1f16ae Ignore .claude/ worktree scratch dir

f0e473048d Author docker-compose stack: llama.cpp (ROCm) + Open WebUI + Qdrant + Lazytainer

19d62aefd3 Merge branch 'research/qwen3.8-27b-tool-calling'

ce1ab05c3e docs: research Qwen3.8-27B Unsloth dynamic GGUF quant + VRAM budget

a55fbcaa18 research: Qwen3.8-27B tool-calling compat with llama.cpp Anthropic shim

haylan created branch main in haylan/LLM-Server

2026-08-24 16:10:04 +00:00

haylan commented on issue haylan/LLM-Server#4

2026-08-24 11:01:37 +00:00

Author the docker-compose stack (llama.cpp + Open WebUI + Qdrant + Lazytainer)

Resolved. Authored docker-compose.yml, .env.example, scripts/download-model.sh, and a top-level README.md quickstart — committed on main (f0e4730).

llama-server: `ghcr.io/ggml-org…

haylan closed issue haylan/LLM-Server#4

2026-08-24 11:01:21 +00:00

Author the docker-compose stack (llama.cpp + Open WebUI + Qdrant + Lazytainer)

haylan commented on issue haylan/LLM-Server#2

2026-08-24 10:17:41 +00:00

Confirm quantization availability for Qwen3.8-27B

Resolved: yes, a dynamic 4-bit XL quant exists.

Repo: unsloth/Qwen3.8-27B-GGUF File: Qwen3.8-27B-UD-Q4_K_XL.gguf (17.6 GB) — confirmed directly from the HF repo's file tree.

VRAM budget…

haylan closed issue haylan/LLM-Server#2

2026-08-24 10:17:03 +00:00

Confirm quantization availability for Qwen3.8-27B

haylan closed issue haylan/LLM-Server#3

2026-08-24 10:16:43 +00:00

Confirm Qwen3.8-27B tool-calling compatibility with llama.cpp's Anthropic Messages API shim

haylan commented on issue haylan/LLM-Server#3

2026-08-24 10:16:43 +00:00

Confirm Qwen3.8-27B tool-calling compatibility with llama.cpp's Anthropic Messages API shim

Answer: No — not confirmed compatible; likely needs a fix, and it may not be a simple chat-template swap this time.

Short version: llama.cpp's Anthropic Messages API shim (PR #17570) just…

haylan opened issue haylan/LLM-Server#6

2026-08-24 10:09:59 +00:00

Write local-usage docs for Claude Code CLI and Kimi CLI against the local endpoint

haylan opened issue haylan/LLM-Server#5

2026-08-24 10:09:58 +00:00

Verify the stack on the real Radeon R9700 box (GPU passthrough + Lazytainer idle-stop)

haylan opened issue haylan/LLM-Server#4

2026-08-24 10:09:57 +00:00

Author the docker-compose stack (llama.cpp + Open WebUI + Qdrant + Lazytainer)

haylan opened issue haylan/LLM-Server#3

2026-08-24 10:09:42 +00:00

Confirm Qwen3.8-27B tool-calling compatibility with llama.cpp's Anthropic Messages API shim

haylan opened issue haylan/LLM-Server#2

2026-08-24 10:09:41 +00:00

Confirm quantization availability for Qwen3.8-27B

haylan opened issue haylan/LLM-Server#1

2026-08-24 10:09:29 +00:00

Local AI inference stack: llama.cpp + Qwen3.8-27B on Radeon R9700

haylan created repository haylan/LLM-Server

2026-08-24 09:48:51 +00:00

haylan deleted branch renovate/symfony from haylan/git-contribution-graph

2026-08-23 20:34:34 +00:00

haylan pushed to main at haylan/git-contribution-graph

2026-08-23 20:34:33 +00:00

466de04c40 Merge pull request 'chore(deps): update symfony packages to v7.4.17' (#25) from renovate/symfony into main

b0f042cc93 chore(deps): update symfony packages to v7.4.17

Compare 2 commits »