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.
7 commits 4 branches 2 tags 203 KiB
Find a file
Claude 78e244f26f
docs: Phase 1 plan review — approved with notes 
- Token.ID = 0 acceptable for Phase 1 (no consumer uses it)
- StopTokens: ignore in Phase 1 (YAGNI)
- serverEnv() should filter existing HIP_VISIBLE_DEVICES before appending
- guessModelType() fine for now, upgrade to /props endpoint in Phase 2
- Integration test build tag approach approved

Charon, 19 Feb 2026

Co-Authored-By: Virgil <virgil@lethean.io>
2026-02-19 20:44:37 +00:00
docs/plans docs: Phase 1 implementation plan 2026-02-19 20:38:11 +00:00
backend.go feat: scaffold go-rocm AMD GPU inference package 2026-02-19 19:39:40 +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 1 plan review — approved with notes 2026-02-19 20:44:37 +00:00
go.mod feat: scaffold go-rocm AMD GPU inference package 2026-02-19 19:39:40 +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: scaffold go-rocm AMD GPU inference package 2026-02-19 19:39:40 +00:00
rocm_stub.go feat: scaffold go-rocm AMD GPU inference package 2026-02-19 19:39:40 +00:00
TODO.md docs: Phase 0 complete — environment validated, llama-server built 2026-02-19 19:57:14 +00:00

README.md

go-rocm

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