core/go-rocm
8
0
Fork 0
Code Issues 4 Pull requests Projects Releases Packages Wiki Activity Actions
AMD ROCm GPU inference for Linux. llama.cpp + HIP backend for RDNA 3.
31 commits 4 branches 2 tags 203 KiB
Find a file
Claude c7c9389749
feat: GGUF metadata parser for model discovery 
Reads GGUF v2/v3 binary headers to extract model metadata (architecture,
name, quantisation type, context length, block count). Includes string
length limits for malformed input protection and uint64 value support
for compatibility with varied GGUF producers.

Co-Authored-By: Virgil <virgil@lethean.io>
2026-02-19 22:20:02 +00:00
docs/plans docs: Phase 3 model support implementation plan 2026-02-19 22:12:31 +00:00
internal feat: GGUF metadata parser for model discovery 2026-02-19 22:20:02 +00:00
backend.go feat: retry port selection in startServer on process failure 2026-02-19 21:40:05 +00:00
CLAUDE.md docs: Phase 0 complete — environment validated, llama-server built 2026-02-19 19:57:14 +00:00
FINDINGS.md docs: Phase 2 complete — robustness features implemented 2026-02-19 21:54:34 +00:00
go.mod feat: llamacpp health check client 2026-02-19 20:50:36 +00:00
go.sum feat: llamacpp health check client 2026-02-19 20:50:36 +00:00
model.go test: graceful shutdown and concurrent request integration tests 2026-02-19 21:50:47 +00:00
README.md Initial commit 2026-02-19 19:35:55 +00:00
register_rocm.go feat: scaffold go-rocm AMD GPU inference package 2026-02-19 19:39:40 +00:00
rocm.go feat: VRAM monitoring via sysfs with dGPU auto-detection 2026-02-19 21:45:02 +00:00
rocm_integration_test.go test: graceful shutdown and concurrent request integration tests 2026-02-19 21:50:47 +00:00
rocm_stub.go feat: VRAM monitoring via sysfs with dGPU auto-detection 2026-02-19 21:45:02 +00:00
server.go fix: only retry startServer on process exit, not timeout 2026-02-19 21:43:06 +00:00
server_test.go feat: retry port selection in startServer on process failure 2026-02-19 21:40:05 +00:00
TODO.md docs: Phase 2 complete — robustness features implemented 2026-02-19 21:54:34 +00:00
vram.go fix: clamp VRAM Free to prevent uint64 underflow 2026-02-19 21:48:19 +00:00
vram_test.go feat: VRAM monitoring via sysfs with dGPU auto-detection 2026-02-19 21:45:02 +00:00

README.md

go-rocm

AMD ROCm GPU inference for Linux. llama.cpp + HIP backend for RDNA 3.