Snider
|
9aaa404397
|
fix(dx): audit coding standards and add tests for untested paths
Security Scan / security (pull_request) Successful in 7s
Test / Vet & Build (pull_request) Failing after 21s
- CLAUDE.md: document coreerr.E() error handling and go-io exclusion
- server_test.go: replace fmt.Errorf with coreerr.E() in test fixtures
- gguf_test.go: add tests for v2 format, skipValue (all type branches),
readTypedValue uint64 path, unsupported version, truncated file
- discover_test.go: add test for corrupt GGUF file skipping
- vram_test.go: add tests for invalid/empty sysfs content
Coverage: 65.8% → 79.2% (+13.4%)
Co-Authored-By: Virgil <virgil@lethean.io>
|
2026-03-17 08:50:17 +00:00 |
|
Snider
|
7915f7ad3c
|
docs: graduate TODO/FINDINGS into production documentation
Co-Authored-By: Virgil <virgil@lethean.io>
|
2026-02-20 15:03:17 +00:00 |
|
Claude
|
68bc7300aa
|
docs: Phase 0 complete — environment validated, llama-server built
- ROCm 7.2, gfx1100 (corrected from gfx1101), kernel 6.17
- llama-server built with HIP from llama.cpp 11c325c
- Gemma3-4B baseline: 109 tok/s decode, 396 tok/s prefill
- Critical: iGPU crash requires HIP_VISIBLE_DEVICES=0
- All Phase 0 tasks marked done
Co-Authored-By: Virgil <virgil@lethean.io>
|
2026-02-19 19:57:14 +00:00 |
|
Snider
|
aa42cff417
|
feat: scaffold go-rocm AMD GPU inference package
Implements inference.Backend via llama-server subprocess (llama.cpp + HIP/ROCm).
Targets RX 7800 XT (gfx1101, RDNA 3, 16GB VRAM).
Includes:
- Backend registration with build tags (linux/amd64)
- Stub backend.go with llama-server lifecycle outline
- CLAUDE.md with build instructions for llama.cpp + ROCm
- TODO.md with 5-phase task queue
- FINDINGS.md with hardware specs, VRAM budget, design rationale
Co-Authored-By: Virgil <virgil@lethean.io>
|
2026-02-19 19:39:40 +00:00 |
|