summaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2026-04-01immich: separate PVs for videos RO/RW to avoid dual-PVC mount issuePaul Buetow
Amp-Thread-ID: https://ampcode.com/threads/T-019d47a3-2deb-75c3-8a75-b0f39006a35d Co-authored-by: Amp <amp@ampcode.com>
2026-04-01immich: per-user external library mounts with RO/RW separationPaul Buetow
Amp-Thread-ID: https://ampcode.com/threads/T-019d47a3-2deb-75c3-8a75-b0f39006a35d Co-authored-by: Amp <amp@ampcode.com>
2026-04-01immich: use bjw-s persistence for external library mountPaul Buetow
Amp-Thread-ID: https://ampcode.com/threads/T-019d47a3-2deb-75c3-8a75-b0f39006a35d Co-authored-by: Amp <amp@ampcode.com>
2026-04-01immich: replace yoga videos with general external library mountPaul Buetow
Amp-Thread-ID: https://ampcode.com/threads/T-019d47a3-2deb-75c3-8a75-b0f39006a35d Co-authored-by: Amp <amp@ampcode.com>
2026-03-29Add newsyslog rotation for dserver logsPaul Buetow
2026-03-28Add OpenBSD build VM and dtail package infrastructurePaul Buetow
Add a QEMU/KVM OpenBSD VM for native compilation of CGo packages (e.g. dtail with DataDog/zstd). The VM is fully automated via expect driving the serial console installer. - packages/buildvm/: setup, provision, start, stop scripts and expect installer - packages/scripts/pkg-dtail-openbsd.sh: multi-binary package with signify signing - packages/Makefile: build VM management and dtail-openbsd target using git archive - frontends/Rexfile: dtail_install task uses custom pkg repo, dtail task enabled Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-28Move package build/upload scripts from gogios Magefile to conf/packagesPaul Buetow
Packaging logic is now OS-agnostic shell scripts + Makefile, reusable for any Go project. Cross-compiles locally, SCPs to target host for native packaging, and uploads to the PV. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-28Sign OpenBSD packages with signify, drop -D unsignedPaul Buetow
Packages are now signed via pkg_sign with the custom-pkg signify key on the OpenBSD build host. The public key at /etc/signify/custom-pkg.pub on each client allows pkg_add to verify without -D unsigned. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-28frontends: install gogios from pkg repo, add pkgrepo_setup taskPaul Buetow
Replace manual binary copy in gogios_install with pkg install (FreeBSD) and pkg_add (OpenBSD). Add pkgrepo_setup task that configures PKG_PATH in root's .profile on OpenBSD frontends. The gogios task now calls gogios_install automatically. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-28pkgrepo: fix test package build scripts for FreeBSD and OpenBSDPaul Buetow
FreeBSD: use -p plist flag so files are actually included in the package. OpenBSD: use -D COMMENT flag and separate desc file as required by pkg_create, auto-detect OS version for repo path. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-28pkgrepo: fix health probe path to /healthzPaul Buetow
The root path returns 404 by design, so probes need a dedicated /healthz endpoint that returns 200. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-28pkgrepo: add FreeBSD/OpenBSD package repository servicePaul Buetow
Serve custom-built FreeBSD and OpenBSD packages via nginx in the k3s cluster. Includes helm chart, ArgoCD app, test artifact build script, and DNS entry via frontends Rexfile. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-22fix: correct NFS sentinel filename in immich-postgres init containerPaul Buetow
The wait-for-nfs init container was checking for nfs.DO_NOT_REMOVE but the actual file on disk is k3svolumes.DO_NOT_REMOVE. This caused every new pod from the rolling update to be permanently stuck in Init:0/1, leaving two postgres pods running indefinitely (old + stuck new).
2026-03-22immich: add NFS mount check init container to postgresPaul Buetow
Amp-Thread-ID: https://ampcode.com/threads/T-019d14d5-4dbf-71a7-a619-d9c5afed3f7c Co-authored-by: Amp <amp@ampcode.com>
2026-03-21Remove obsolete documentation snippetsPaul Buetow
2026-03-21movedPaul Buetow
2026-03-20Parallelize delete-both VM teardownPaul Buetow
2026-03-20Add Pi VM launcher scriptsPaul Buetow
2026-03-20Add project Pi VM model switching configPaul Buetow
2026-03-20fix wireguard setup ssh host pinningPaul Buetow
2026-03-20task 301: extract provisioning collaboratorsPaul Buetow
2026-03-20task 300: persist effective service modePaul Buetow
2026-03-20task 299: clean up local state on deletePaul Buetow
2026-03-20task 298: pin SSH host keys per VM statePaul Buetow
2026-03-20task 297: lock down default ingress rulesPaul Buetow
2026-03-20Remove peers by allowed IPs from local WireGuard configPaul Buetow
2026-03-20Initial commit: add hyperstack-vm1.toml, hyperstack-vm2.toml, update ↵Paul Buetow
hyperstack.rb and wg1-setup.sh for multi-VM WireGuard support
2026-03-18vllm: skip docker pull on model switch, persist torch compile cachePaul Buetow
- model switch now passes pull_image: false to avoid surprise multi-GB image downloads when the upstream vLLM image was updated upstream; docker pull is still run on initial install (pull_image: true default) - mount /ephemeral/vllm_cache → /root/.cache/vllm so torch.compile artifacts survive container restarts; saves ~30-60 s on warm switches - add vllm_compile_cache_dir helper (sibling of hug_cache_dir) Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
2026-03-18gpt-oss-120b: revert to 131072 — hard architecture limitPaul Buetow
max_position_embeddings=131072 in model config.json; exceeding it causes NaN/CUDA OOB. 163840 was rejected by vLLM at startup. The 135K error requires starting a fresh opencode conversation instead. Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
2026-03-18gpt-oss-120b: raise max_model_len to 163840 (160K)Paul Buetow
131K was still too small — observed 135K token conversations in practice. Physical KV capacity is 168K blocks so 160K is safe without OOM. Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
2026-03-18gpt-oss-120b: raise max_model_len to 131072Paul Buetow
MXFP4 KV cache is compact enough that vLLM allocated 168K token blocks (10560×16) at 0.92 utilization — the 40K limit was too conservative and caused negative max_tokens errors in long Claude Code sessions. Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
2026-03-18fix: handle bundler self_manager.rb error with Errno::ENOENTPaul Buetow
2026-03-18fix: refactor CLI help to DRY up duplicated codePaul Buetow
2026-03-18cli: show help when called without argumentsPaul Buetow
2026-03-18refactor: Split Config class per SRPPaul Buetow
- Created ConfigLoader for TOML loading and validation - Kept Config for configuration value access only - Reduced Config from 489 lines to ~200 lines - Fixed CLI to use ConfigLoader and pass @path to Config
2026-03-18hyperstack status: display active vLLM modelPaul Buetow
Show the currently loaded model (from state file, or config default) so it's immediately visible without running `model list`. Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
2026-03-18nemotron-super: set max_model_len=262144 (256K); document NoPE and OOM riskPaul Buetow
Tested 1M context (NoPE allows arbitrary max_position_embeddings without YaRN) — OOMs on A100 80GB due to insufficient VRAM after 60GB model weights. 256K (262144) is the practical ceiling on this hardware. Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
2026-03-18nemotron-super: use qwen3_xml tool call parser — same XML format, worksPaul Buetow
Both Nemotron and Qwen3-XML use identical <tool_call><function=name> <parameter=p>value</parameter></function></tool_call> format. qwen3_xml correctly parses Nemotron's output; tool calling now works with opencode and other API clients. Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
2026-03-18nemotron-super: revert to no tool calling; add nemotron_v3 reasoning parserPaul Buetow
vLLM 0.17.1 has no tool call parser for Nemotron's custom XML format (<tool_call><function=...><parameter=...>). Setting llama3_json produced garbage output. Reverted to tool_call_parser="" with a clear comment. Added --reasoning-parser nemotron_v3 via extra_vllm_args so <think> tokens are properly exposed as reasoning_content in the API response. For agentic work requiring tool calls, switch to qwen3-coder-next or devstral. Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
2026-03-18Fix nemotron-super tool_call_parser; auto-clear WireGuard hostname from ↵Paul Buetow
known_hosts - hyperstack-vm.toml: set tool_call_parser=llama3_json for nemotron-super so vLLM accepts tool_choice requests from opencode; model won't spontaneously call tools so the vLLM 0.17.1 token_ids crash in llama3_json won't trigger - hyperstack.rb: wait_for_ssh now also removes the WireGuard hostname (hyperstack.wg1) from known_hosts alongside the IP, preventing StrictHostKeyChecking failures across VM recreates Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
2026-03-18Add extra_vllm_args support; fix nemotron-super to real 120B; add ↵Paul Buetow
deepseek-r1-32b, qwen3-32b, devstral presets - hyperstack.rb: add extra_vllm_args array field to preset resolver and vllm_install_script; flags are appended verbatim to the docker run command, enabling per-preset vLLM flags (reasoning parsers, Mistral loader) - hyperstack.rb: show extra_args in dry-run model switch output - hyperstack-vm.toml: fix nemotron-super to use actual NVIDIA Nemotron-3-Super-120B-A12B AWQ (cyankiwi) with trust_remote_code=true; previous preset incorrectly used llama-3.3-70b - hyperstack-vm.toml: add deepseek-r1-32b (--reasoning-parser deepseek_r1, ~18 GB) - hyperstack-vm.toml: add qwen3-32b (--reasoning-parser deepseek_r1, ~18 GB) - hyperstack-vm.toml: add devstral (Mistral tokenizer+config format, ~15 GB); --load_format mistral omitted because AWQ weights are in standard HF safetensors format All 6 new/updated presets end-to-end tested on A100 80GB (vLLM 0.17.1). Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
2026-03-18Add gpt-oss, qwen25-coder-32b, qwen3-coder-30b presets; use hostname for ↵Paul Buetow
WireGuard New vLLM model presets (all end-to-end tested on A100 80GB): - gpt-oss-20b: openai/gpt-oss-20b — MoE 20B, ~14 GB MXFP4, ultra-fast (3.6B active) - gpt-oss-120b: openai/gpt-oss-120b — MoE 120B, ~65 GB MXFP4, powerful reasoning - qwen25-coder-32b: Qwen/Qwen2.5-Coder-32B-Instruct-AWQ — ~18 GB, best 32B coder - qwen3-coder-30b: QuantTrio/Qwen3-Coder-30B-A3B-Instruct-AWQ — ~18 GB Qwen3 coder gpt-oss models disable --enable-auto-tool-choice (tool_call_parser = ""): vLLM 0.17.1's llama3_json parser crashes on gpt-oss responses because the new token_ids field in the response is passed as an unexpected keyword argument to extract_tool_calls(). gpt-oss-120b max_model_len raised to 40960: Claude Code's system prompt alone is ~33K tokens, so 16K was insufficient. 40K allows Claude Code to connect with headroom. Use wireguard_gateway_hostname (hyperstack.wg1) instead of raw 192.168.3.1 IP for all connection URLs (tests, ready message, dry-run output). The hostname is derived from the wg interface name and resolves via /etc/hosts. Fix test max_tokens: raised from 50 to 500 so reasoning models (e.g. gpt-oss) have enough tokens to complete chain-of-thought before producing content. Fix qwen25-coder-32b max_model_len: model config has max_position_embeddings=32768, not 128K as assumed. Using 65536 caused a vLLM pydantic validation error. Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
2026-03-18Fix nemotron-super preset and test_vllm model detectionPaul Buetow
Replace cyankiwi/Llama-3_3-Nemotron-Super-49B-v1_5-AWQ-4bit with casperhansen/llama-3.3-70b-instruct-awq for the nemotron-super preset. The NAS model's config.json has num_key_value_heads=null by design for its heterogeneous per-layer attention architecture, which is incompatible with vLLM's pydantic ModelConfig validation (requires int). No working AWQ quant for this architecture exists; Llama-3.3-70B-Instruct AWQ is a proven drop-in for the extended-analysis use case. Also fix test_vllm to use the model reported by /v1/models instead of the static config default, so tests pass after a model switch. Add trust_remote_code support to vllm_install_script for future models that require custom HuggingFace model code. Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
2026-03-18Add vLLM model presets and live model switchingPaul Buetow
- New [vllm.presets.*] TOML section with two presets: qwen3-coder-next bullpoint/Qwen3-Coder-Next-AWQ-4bit (256k ctx, coding) nemotron-super solidrust/Llama-3.3-Nemotron-Super-49B-v1-AWQ (131k ctx, analysis) - New CLI subcommand: `model list` — show presets, mark the active one - New CLI subcommand: `model switch PRESET [--dry-run]` — switch the running VM to a different preset without redeploying: 1. stops old Docker container (if container_name differs) 2. starts new container and waits for model readiness 3. hot-reloads LiteLLM config via litellm_reload_script (no venv reinstall) 4. updates state file with new vllm_model / vllm_container_name / vllm_preset - New `create --model PRESET` flag — deploy with a non-default preset - vllm_install_script and litellm_install_script now accept preset_config:/ model_override: so callers can override individual fields without duplicating the full config - State file now tracks vllm_container_name and vllm_preset for clean container lifecycle management across switches Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
2026-03-18Use hyperstack.wg1 hostname instead of hardcoded IP in READMEPaul Buetow
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
2026-03-18Add vLLM + LiteLLM support; rename script; add READMEPaul Buetow
- Replace Ollama (disabled by default) with vLLM Docker container + LiteLLM Anthropic-API proxy as the default inference backend - vLLM setup: pulls vllm/vllm-openai, starts container on port 11434, polls until model is loaded (up to 10 min for first 45 GB download) - LiteLLM setup: installs in Python venv, writes config mapping Claude model aliases to the vLLM model, runs as a systemd service on port 4000 - New CLI flags on `create`: --vllm/--no-vllm, --ollama/--no-ollama to override config at runtime - New `test` command: end-to-end inference test over WireGuard against vLLM (/v1/models + /v1/chat/completions) and LiteLLM (/v1/messages) - UFW rules now open both port 11434 (inference) and 4000 (LiteLLM) from the WireGuard subnet - Rename hyperstack_vm.rb → hyperstack.rb - Add README.md with quickstart, Claude Code / OpenCode usage, CLI reference, monitoring commands, and VRAM sizing notes - Add vllm-setup.txt: detailed manual setup notes and architecture docs Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
2026-03-16Update hyperstack VM bootstrap, WireGuard, and Ollama setup logic; add ↵Paul Buetow
retries, apt lock waits, and model verification
2026-03-15cleanupPaul Buetow
2026-03-15Add Hyperstack VM automation and model defaultsPaul Buetow
2026-03-14Update project config, remove CLAUDE.md, add Gemfile and Rakefile for rcmPaul Buetow
generated by cgit v1.2.3 (git 2.25.1) at 2026-08-07 13:24:20 +0000