The dollar-brace in sed end-of-file pattern was interpreted as
TypeScript template literal interpolation. Use escaped syntax
to insert a literal dollar sign.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Replace in-memory array storage with persistent file-based logging:
- Logs written to /tmp/ollama37-session-{timestamp}.log
- Text markers: ===MARKER:START:{ID}:{TIMESTAMP}=== for test boundaries
- Extract test-specific logs via sed to /tmp/test-{ID}-logs.txt
- Write queue prevents race conditions between log data and markers
- Line buffering prevents marker injection mid-line
- Auto-cleanup of session files older than 24 hours
Benefits:
- Crash resilient: logs persist even if test process dies
- Bounded memory: no array growth, only file I/O
- Precise boundaries: text markers unaffected by buffering delays
API unchanged - all existing integrations (executor, cli, test cases) work without modification.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Replace command-heavy documentation with conceptual explanation:
- Project goal and infrastructure rationale
- Test framework philosophy (exit codes lie, logs tell truth)
- Dual-judge architecture design
- Log collection problem and solution
- Test execution flow
- Model unload strategy
- Design decisions with reasoning
- Known limitations
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- stop() could resolve promise twice (from close event AND timeout)
- Add resolved flag to ensure single resolution
- Add comment about parallel execution limitation in executor
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Problem: Tests used `docker compose logs --since=5m` which caused:
- Log overlap between tests
- Logs from previous tests included
- Missing logs if test exceeded 5 minutes
Solution:
- New LogCollector class runs `docker compose logs --follow`
- Marks test start/end boundaries
- Writes test-specific logs to /tmp/test-{testId}-logs.txt
- Test steps access via TEST_ID environment variable
Changes:
- tests/src/log-collector.ts: New LogCollector class
- tests/src/executor.ts: Integrate LogCollector, set TEST_ID env
- tests/src/cli.ts: Start/stop LogCollector for runtime/inference
- All test cases: Use log collector with fallback to docker compose
Also updated docs/CICD.md with:
- Test runner CLI documentation
- Judge modes (simple, llm, dual)
- Log collector integration
- Updated test case list (12b, 27b models)
- Model unload strategy
- Troubleshooting guide
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- TC-INFERENCE-003: Add unload step for gemma3:4b at end
- TC-INFERENCE-004: Remove redundant 4b unload at start
- TC-INFERENCE-005: Remove redundant 12b unload at start
Each model size test now handles its own VRAM cleanup.
Workflow-level unload remains as safety fallback for failures.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- TC-INFERENCE-004: gemma3:12b single GPU test
- TC-INFERENCE-005: gemma3:27b dual-GPU test (K80 layer split)
- Each test unloads previous model before loading next
- Workflows unload all 3 model sizes after inference suite
- 27b test verifies both GPUs have memory allocated
- Add unloadModel() method to LLMJudge class
- CLI calls unloadModel() after judging completes
- Workflows unload gemma3:4b after inference tests
- Uses Ollama API with keep_alive:0 to trigger unload
Change judge.ts progress message from console.log (stdout) to
process.stderr.write (stderr) to prevent 'Judging batch...' message
from contaminating JSON output when using --output json flag.
- Add step results, timing context, and build notes to LLM prompt
- LLM now sees exit codes, durations, and simple judge result
- Add guidance that long build times within timeout are acceptable
- Add separate simple/LLM verdict tracking in dual-judge mode
- Console output shows both Simple and LLM pass/fail status
- JSON summary includes separate simple/llm breakdown
- Each test report includes simplePass/llmPass fields
This helps distinguish between simple judge failures (exit code != 0)
and LLM judge failures (semantic analysis), making debugging easier.
- Add OLLAMA_VERSION build arg to Dockerfiles
- Update Makefile to pass version via --build-arg
- Add .env.example as local development reference
- Update build.yml to use cicd-1 environment for vars.OLLAMA_VERSION
Fixes#8🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Update CLAUDE.md build command to include -ldflags that sets
the version properly instead of defaulting to 0.0.0.
Fixes#8🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Remove CUDA initialization checks from TC-RUNTIME-002 (ggml_cuda_init,
load_backend only appear when a model is loaded, not at startup)
- Fix bash integer comparison error in TC-RUNTIME-003
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Rename step to "Verify UVM device files" for clarity
- Add "WARNING:" prefix when UVM device is missing
- Add "SUCCESS:" prefix when device is present
- Add confirmation message after UVM fix is applied
- Separate ls command for cleaner output
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
New options:
- --dual-judge: Run both simple and LLM judge, fail if either fails
- --judge-url: Separate LLM Judge server URL (default: localhost:11435)
- --judge-model: Model for LLM judging (default: gemma3:4b)
Dual judge logic:
- Simple judge checks exit codes
- LLM judge analyzes logs semantically
- Final result: FAIL if either judge says FAIL
- Combines reasons from both judges on failure
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add cicd/docker-compose.judge.yml for stable reference Ollama
- Runs on port 11435 (separate from test subject on 11434)
- Uses dogkeeper886/ollama37:latest from DockerHub
- Add cicd/README.md documenting CI infrastructure
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The '|| true' was swallowing test runner exit codes, causing workflows
to pass even when tests failed. Added separate 'Check test results'
step that reads JSON summary and fails workflow if any tests failed.
Affected workflows:
- build.yml
- runtime.yml
- inference.yml
- full-pipeline.yml
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Strip ANSI escape codes from stdout/stderr to reduce log size
(spinner animations were ~95% of inference log size)
- Add [TIMEOUT] indicator when commands are killed due to timeout
for clearer failure diagnosis
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Tesla K80 needs ~60-180s to load model into VRAM on first inference.
Add warmup step with 5-minute timeout to preload model before
subsequent inference tests run.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Redundant test - if TC-INFERENCE-002 (Basic Inference) passes,
CUBLAS fallback is already working. Any errors would cause
inference to fail, making a separate error-check test unnecessary.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add step to check/create /dev/nvidia-uvm device files
- Use nvidia-modprobe -u -c=0 if UVM devices missing
- Restart container after creating UVM devices
- Update criteria to clarify GPU detection requirements
- Increase timeout to 120s for container restart
Fixes issue where nvidia-smi works but Ollama only detects CPU.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Timeout: 900s -> 3600s (60 min) for runtime image build
- Add tee to capture full build log to /tmp/build-runtime.log
- Add step to show last 200 lines of build log for debugging
- Helps diagnose build failures with proper log capture
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Separate workflows for flexibility:
- build.yml: Build verification (standalone + reusable)
- runtime.yml: Container & runtime tests with container lifecycle
- inference.yml: Inference tests with optional container management
- full-pipeline.yml: Orchestrates all stages with LLM judge
Each workflow can be triggered independently for targeted testing,
or run the full pipeline for complete validation.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Separate progress output (stderr) from JSON results (stdout)
- Add timestamps, test counters, and step progress to executor
- Update CLI to use stderr for progress messages
- Update workflow to capture JSON to file while showing progress
- Add --silent flag to suppress npm banner noise
This allows real-time visibility into test execution during CI runs
while preserving clean JSON output for artifact collection.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Remove automatic triggers on push/PR to avoid slow builds running
unexpectedly. Use workflow_dispatch for manual control.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add .github/workflows/build-test.yml for automated testing
- Add tests/ directory with TypeScript test runner
- Add docs/CICD.md documentation
- Remove .gitlab-ci.yml (migrated to GitHub Actions)
- Update .gitignore for test artifacts
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Problem: Model loading takes 2-3 minutes on first load with no user feedback,
causing confusion about whether the system is frozen or working.
Root Cause: GPU initialization (reserveWorstCaseGraph) takes ~164 seconds on
Tesla K80 GPUs due to CUDA kernel compilation (PTX JIT for compute 3.7). This
is by design - it validates GPU compatibility before committing to full load.
Solution:
1. Add comprehensive timing instrumentation to identify bottlenecks
2. Add user-facing progress messages explaining the delay
Changes:
- cmd/cmd.go: Update spinner with informative message for users
- llama/llama.go: Add timing logs for CGO model loading
- runner/llamarunner/runner.go: Add detailed timing for llama runner
- runner/ollamarunner/runner.go: Add timing + stderr messages for new engine
- server/sched.go: Add timing for scheduler load operation
User Experience:
Before: Silent wait with blinking cursor for 2-3 minutes
After: Rotating spinner with message "loading model (may take 1-3 min on first load)"
Performance Metrics Captured:
- GGUF file reading: ~0.4s
- GPU kernel compilation: ~164s (bottleneck identified)
- Model weight loading: ~0.002s
- Total end-to-end: ~165s
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Extends the Docker Makefile with targets for building from local source code without pushing to GitHub, enabling faster iteration during development.
New build targets:
- build-runtime-local: Build from local source with cache
- build-runtime-local-no-cache: Full rebuild from local source
- build-runtime-no-cache: Force fresh GitHub clone without cache
Added docker/runtime/Dockerfile.local for local source builds, mirroring the GitHub-based Dockerfile structure but using COPY instead of git clone.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
1. Fix binary path resolution using symlink (docker/runtime/Dockerfile)
- Build binary to source directory (./ollama)
- Create symlink from /usr/local/bin/ollama to /usr/local/src/ollama37/ollama
- Allows ml/path.go to resolve libraries via filepath.EvalSymlinks()
- Fixes "total vram=0 B" issue without requiring -w flag
2. Add comprehensive logging for model loading phases (llm/server.go)
- Log runner subprocess startup and readiness
- Log each memory allocation phase (FIT, ALLOC, COMMIT)
- Log layer allocation adjustments during convergence
- Log when model weights are being loaded (slowest phase)
- Log progress during waitUntilRunnerLaunched (every 1s)
- Improves visibility during 1-2 minute first-time model loads
3. Fix flash attention compute capability check (ml/device.go)
- Changed DriverMajor to ComputeMajor for correct capability detection
- Flash attention requires compute capability >= 7.0, not driver version
These changes improve user experience during model loading by providing
clear feedback at each stage, especially during the slow COMMIT phase
where GGUF weights are loaded and CUDA kernels compile.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Redesigned the Docker build system from a single-stage monolithic design to a clean
two-stage architecture that separates build environment from compilation process while
maintaining library path compatibility.
## Architecture Changes
### Builder Image (docker/builder/Dockerfile)
- Provides base environment: CUDA 11.4, GCC 10, CMake 4, Go 1.25.3
- Built once, cached for subsequent builds (~90 min first time)
- Removed config file copying (cuda-11.4.sh, gcc-10.conf, go.sh)
- Added comprehensive comments explaining each build step
- Added git installation for runtime stage source cloning
### Runtime Image (docker/runtime/Dockerfile)
- Two-stage build using ollama37-builder as base for BOTH stages
- Stage 1 (compile): Clone source from GitHub → CMake configure → Build C/C++/CUDA → Build Go
- Stage 2 (runtime): Copy artifacts from stage 1 → Setup environment → Configure server
- Both stages use identical base image to ensure library path compatibility
- Removed -buildvcs=false flag (VCS info embedded from git clone)
- Comprehensive comments documenting library paths and design rationale
### Makefile (docker/Makefile)
- Simplified from 289 to 145 lines (-50% complexity)
- Removed: run, stop, logs, shell, test targets (use docker-compose instead)
- Removed: build orchestration targets (start-builder, copy-source, run-cmake, etc.)
- Removed: artifact copying (handled internally by multi-stage build)
- Focus: Build images only (build, build-builder, build-runtime, clean, help)
- All runtime operations delegated to docker-compose.yml
### Documentation (docker/README.md)
- Completely rewritten for new two-stage architecture
- Added "Build System Components" section with file structure
- Documented why both runtime stages use builder base (library path compatibility)
- Updated build commands to use Makefile
- Updated runtime commands to use docker-compose
- Added comprehensive troubleshooting section
- Added build time and image size tables
- Reference to archived single-stage design
## Key Design Decision
**Problem**: Compiled binaries have hardcoded library paths
**Solution**: Use ollama37-builder as base for BOTH compile and runtime stages
**Trade-off**: Larger image (~18GB) vs guaranteed library compatibility
## Benefits
- ✅ Cleaner separation of concerns (builder env vs compilation vs runtime)
- ✅ Builder image cached after first build (90 min → <1 min rebuilds)
- ✅ Runtime rebuilds only take ~10 min (pulls latest code from GitHub)
- ✅ No library path mismatches (identical base images)
- ✅ No complex artifact extraction (multi-stage COPY)
- ✅ Simpler Makefile focused on image building
- ✅ Runtime management via docker-compose (industry standard)
## Files Changed
Modified:
- docker/builder/Dockerfile - Added comments, removed COPY config files
- docker/runtime/Dockerfile - Converted to two-stage build
- docker/Makefile - Simplified to focus on image building only
- docker/README.md - Comprehensive rewrite for new architecture
Deleted:
- docker/builder/README.md - No longer needed
- docker/builder/cuda-11.4.sh - Generated in Dockerfile
- docker/builder/gcc-10.conf - Generated in Dockerfile
- docker/builder/go.sh - Generated in Dockerfile
Archived:
- docker/Dockerfile → docker/Dockerfile.single-stage.archived
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Replaced complex two-stage build (builder → runtime) with single-stage
Dockerfile that builds and runs Ollama in one image. This fixes model
loading issues caused by missing CUDA libraries and LD_LIBRARY_PATH
mismatches in the previous multi-stage design.
Changes:
- Add docker/Dockerfile: Single-stage build with GCC 10, CMake 4, Go 1.25.3, CUDA 11.4
- Clone source from https://github.com/dogkeeper886/ollama37
- Compile Ollama with "CUDA 11" preset for Tesla K80 (compute capability 3.7)
- Keep complete CUDA toolkit and all libraries in final image (~20GB)
- Update docker-compose.yml: Simplified config, use ollama37:latest image
- Update docker/README.md: New build instructions and architecture docs
Trade-off: Larger image size (~20GB vs ~3GB) for guaranteed compatibility
and reliable GPU backend operation. All libraries remain accessible with
correct paths, ensuring models load properly on Tesla K80.
Tested: Successfully runs gemma3:1b on Tesla K80
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
This change prevents permission issues when using Ollama both locally and
in Docker by:
- Running container as host user (UID/GID) instead of root
- Mounting host's $HOME/.ollama directory using environment variables
- Setting HOME environment variable in container
This allows both the local binary and Docker container to share the same
model data without permission conflicts or duplication.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add LD_LIBRARY_PATH to CMake and build steps for GCC 10 libraries
- Copy GCC 10 runtime libraries (libstdc++.so.6, libgcc_s.so.1) to output
- Update runtime Dockerfile to use minimal CUDA runtime packages
- Add -buildvcs=false flag to Go build to avoid Git VCS errors
- Simplify runtime container to only include necessary CUDA libraries
- Fix library path configuration for proper runtime library loading
- Build CUDA 11.4 toolkit from NVIDIA repository (for K80 compute 3.7 support)
- Build GCC 10 from source (required for CUDA 11.4 compatibility)
- Build CMake 4.0.0 from source (latest version)
- Install Go 1.25.3 from official tarball
- Configure library paths via /etc/ld.so.conf.d/gcc-10.conf and ldconfig
- Add /etc/profile.d scripts for interactive shell PATH setup
- Use ENV statements for Docker build-time and runtime PATH configuration
- Switch from nvidia/cuda base image to rockylinux:8 for full control
- Add cleanup step in copy-source target to remove build/, ollama, and dist/
- Prevents host build artifacts from interfering with container builds
- Ensures clean build environment when switching between host and Docker workflows
- docker cp doesn't respect .dockerignore, so explicit cleanup is needed
- Remove CMAKE_C_COMPILER and CMAKE_CXX_COMPILER from CUDA 11 presets
- Allows CMake to auto-detect system GCC instead of hardcoding /usr/local/bin/gcc
- Improves portability across different systems (host, Docker containers, etc.)
- Users can still override compiler via CC/CXX environment variables if needed
