core/go-rocm
8
0
Fork 0
Code Issues 4 Pull requests Projects Releases Packages Wiki Activity Actions 4
AMD ROCm GPU inference for Linux. llama.cpp + HIP backend for RDNA 3.
17 commits 4 branches 2 tags 203 KiB
Find a file
Claude 0e68d71c8a
test: integration tests for full ROCm inference pipeline 
LoadModel → Generate → Chat → Close on real AMD GPU hardware.
Build-tagged //go:build rocm so normal go test skips them.

Co-Authored-By: Virgil <virgil@lethean.io>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-19 21:15:02 +00:00
docs/plans docs: incorporate Charon review — safer serverEnv() filtering 2026-02-19 20:47:16 +00:00
internal/llamacpp fix: guard response body lifecycle in SSE streaming client 2026-02-19 21:04:02 +00:00
backend.go feat: Backend Available() and LoadModel() with GPU detection 2026-02-19 21:12:02 +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: 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 feat: TextModel implementation wrapping llama-server 2026-02-19 21:11:55 +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_integration_test.go test: integration tests for full ROCm inference pipeline 2026-02-19 21:15:02 +00:00
rocm_stub.go feat: scaffold go-rocm AMD GPU inference package 2026-02-19 19:39:40 +00:00
server.go feat: server lifecycle and helpers for llama-server subprocess 2026-02-19 21:08:07 +00:00
server_test.go feat: Backend Available() and LoadModel() with GPU detection 2026-02-19 21:12:02 +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.