3 people ab3c763845 fix(llamacpp): pin image to server-cuda-b9246 (rolling tag broke at b9282) (#188) ...

The upstream rolling `ghcr.io/ggml-org/llama.cpp:server-cuda` tag regressed at
b9282 — `llama-server` crash-loops with `libllama-common.so.0: cannot open
shared object file` (broken lib packaging). Since our composes defaulted to the
rolling tag, every fresh pull of llamacpp/default + llamacpp/mtp-vision hit the
crash loop and the endpoint never came up. Reported in #187.

Pin both single-card composes to the validated build `server-cuda-b9246`
(2026-05-20 — the build all current BENCHMARKS rows were measured on). Override
to follow a newer build via LLAMACPP_IMAGE once validated. README + engine
profile notes updated to match.

Closes #187.

Co-authored-by: noonghunna <[email protected]>
Co-authored-by: Claude Opus 4.7 (1M context) <[email protected]>

2026-05-23 00:45:21 +05:00

..

lib

fix(llamacpp): pin image to server-cuda-b9246 (rolling tag broke at b9282) (#188)

2026-05-23 00:45:21 +05:00

maintenance

fix(tools): resolve profile image pins in audit

2026-05-14 21:41:06 +00:00

tests

llama.cpp single: thinking-off policy alignment + MTP profile family

2026-05-20 01:01:26 +00:00

bench.sh

scripts: endpoint-first --url/--model/--engine for non-Docker engines (#174)

2026-05-21 04:07:50 +05:00

detect_nvlink.sh

feat(nvlink): auto-detect NVLink on N-GPU topologies; add detection to multi4 + gemma-4-26b dual

2026-05-18 19:31:39 +00:00

diagnose-estate.sh

feat(launch): add estate planner orchestration

2026-05-14 17:04:38 +00:00

diagnose-profile.sh

feat(scripts): add diagnose-profile triage

2026-05-14 22:07:00 +00:00

generate-compose.sh

v0.8.0 STEP 3+4: compose generator + 5-triple golden-parity test (#141)

2026-05-16 15:49:37 +00:00

gpu-mode.sh

gpu-mode status: probe :8020 + detect engine on :8030

2026-05-20 02:30:31 +00:00

health.sh

…

launch.sh

fix(launch): single-card default suggestion → llamacpp/default (#185)

2026-05-22 21:32:49 +05:00

power-cap-sweep.sh

feat(power-cap-sweep): --include-commit flag stamps club-3090 git SHA in report header (closes #112)

2026-05-10 17:57:20 +00:00

preflight.sh

scripts: endpoint-first --url/--model/--engine for non-Docker engines (#174)

2026-05-21 04:07:50 +05:00

pull.sh

feat(pull): v0.8.2 STEP V2 — surface pointer + --submit-last/--submit (gh + gh-less, consented, F5 reuse)

2026-05-18 17:37:41 +00:00

quality-test.sh

fix(rebench): always capture sandboxed-pack logs to the per-tag results dir (#179)

2026-05-22 20:50:51 +05:00

rebench-full.sh

fix(rebench): always capture sandboxed-pack logs to the per-tag results dir (#179)

2026-05-22 20:50:51 +05:00

rebench-report.py

feat(bench): surface prompt processing throughput

2026-05-15 09:03:10 +00:00

rebench-runtime.sh

feat(models): add ik_llama Qwen3.6-27B IQ4_KS composes — text 262K + vision 160K (#180)

2026-05-22 04:45:44 +05:00

report.sh

report.sh: capture image digest + OCI labels (build tag, upstream commit)

2026-05-20 13:25:44 +00:00

setup.sh

feat(scripts): add hardware-aware setup picker

2026-05-13 20:44:35 +00:00

soak-helper.py

docs(soak-test): clarify PASS verdict semantics — closes #140

2026-05-15 22:18:09 +05:00

soak-test.sh

docs(soak-test): clarify PASS verdict semantics — closes #140

2026-05-15 22:18:09 +05:00

submit-bench.sh

fix(scripts): make submit-bench issue-first

2026-05-13 18:40:43 +00:00

switch.sh

refactor(llamacpp): collapse single-card composes 3→2 (default = mtp alias) (#181)

2026-05-22 20:50:47 +05:00

update.sh

feat: detect repo drift in preflight + add scripts/update.sh

2026-05-03 12:17:04 +00:00

verify-full.sh

fix(verify-full): warm engine before scored checks (closes #352)

2026-05-15 23:02:31 +00:00

verify-stress.sh

docs: laptop EC-managed power + TQ3 vs fp8 KV naming-trap; verify-stress: auto-bump curl timeout under VLLM_ENFORCE_EAGER

2026-05-09 10:19:23 +00:00

verify.sh

fix(verify): drop tail buffer on Genesis check 2 anchor (refines 95b0905)

2026-05-02 11:41:12 +00:00