3 people 8eff77e2be Add Tess-4-27B to the catalog (llama.cpp dual, external MTP, 262K) (#661) ...

Qwen3.5-based dense 27B (migtissera Q4_K_M GGUF); arch qwen35-dense,
64 layers, standard GQA — confirmed from the GGUF header. First
EXTERNAL-MTP compose in the catalog: the nextn draft ships as a
separate mtp-*.gguf, engaged via --spec-draft-model + --spec-type
draft-mtp (vs Deckard's embedded head).

Live-validated on dual 3090 (2026-07-09): serves at 262K, decode
~52 narr / 68 code, verify-stress 8/8 (NIAH clean to 240,634 tok),
soak-continuous PASS, 8-pack 115/150 think-off / 118/150 think-on —
ties/edges the qwen3.6-27b dual-max (109) and leads the agentic packs
(hermes 15/20 vs 9, cli-40 25/40 vs 20). Ships as caveats: streaming
tool-calls + thinking-ON -> finish=length (thinking-off for tools).

- models/tess-4-27b.yml + drafters/tess-mtp-gguf.yml (spec_method mtp_gguf)
- add mtp_gguf to llama-cpp-mainline supported_drafters (live-validated,
  additive — mainline serves external draft-mtp on b9246)
- compose dual/migtissera-q4km/mtp.yml + registry entry + DEFAULTS row
- bump catalog counts (registry 62, disk 63, models 12, drafters 12)
- BENCHMARKS.md: Tess dual-card section with dual-max comparison


Claude-Session: https://claude.ai/code/session_01EfF565T9eSLaqGzidyJ1Pm

Co-authored-by: noonghunna <[email protected]>
Co-authored-by: Claude Opus 4.8 (1M context) <[email protected]>

2026-07-09 21:45:38 +05:00

..

fixtures

serve: neutral primary model name (qwen3.6-27b / gemma-4-31b), keep -autoround alias

2026-07-02 11:28:31 +00:00

lib

Add Tess-4-27B to the catalog (llama.cpp dual, external MTP, 262K) (#661)

2026-07-09 21:45:38 +05:00

maintenance

fix(tools): resolve profile image pins in audit

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

systemd

tools: add HTTP model-switch service (thin wrapper over switch.sh)

2026-07-03 17:44:17 -07:00

tests

Add Tess-4-27B to the catalog (llama.cpp dual, external MTP, 262K) (#661)

2026-07-09 21:45:38 +05:00

arch-ab.sh

fp8w on Blackwell: auto-disable DeepGEMM + --force the arch-ab arm

2026-07-05 07:21:34 +00:00

beellama-pin-bump.sh

feat(beellama): release v0.3.0 Q8_K_XL dual composes (experimental) + centralize image pin (#296)

2026-06-02 16:35:48 +05:00

bench-agentic.sh

feat(bench-agentic): decouple context ramp from tool-call success (#255) (#396)

2026-06-13 18:53:54 +05:00

bench.sh

catalog-baselines slice 2c: canonical two-depth prefill/TTFT probe + anchor calibration

2026-07-04 16:22:48 +00:00

c3t

Add c3t — the club-3090 test-console TUI (built by Qwen Max from the spec) (#428)

2026-06-18 07:31:02 +05:00

catalog-baseline.sh

baselines: quality_env harness provenance on quality rows (friction #8)

2026-07-05 09:55:54 +00:00

concurrency-probe.sh

Phase 2: validation-grade concurrency-probe (per-stream TPS, VALIDATE, SWEEP)

2026-07-05 06:41:07 +00:00

detect_nvlink.sh

detect_nvlink: auto-enable PCIe P2P when nvidia-smi reports it OK

2026-06-24 14:07:06 +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

chore(254): deprecate the now-unused Genesis nightly engines + patches [Phase 3+4]

2026-06-05 14:44:21 +00:00

gpu-mode.sh

c3/gpu-mode: preview-clip fix + scene-boundary hardening (F2+F5, T1-lite tail)

2026-07-04 11:12:32 +00:00

health.sh

Phase 2b: add --json/CLI contracts to 7 stack scripts (additive)

2026-06-18 08:43:00 +00:00

launch.sh

fix(launcher): GGUF verify-glob (#634) + .env engine-image passthrough (#632) (#639)

2026-07-08 12:52:47 +05:00

pod.sh

refactor(pods): rename cluster → pod (#610) + heterogeneous-rig guidance

2026-07-07 02:10:17 +00:00

power-cap-sweep.sh

Operational robustness (#281): orphan-safe switch.sh · reboot-surviving vLLM · multi-GPU power sweep (#285)

2026-05-31 22:13:52 +05:00

preflight.sh

preflight: warn on single-card GPU_MEMORY_UTILIZATION override above default (#641)

2026-07-08 23:18:33 +05:00

pull.sh

c3+pull: detect in-progress downloads + per-repo lock (#617) (#644)

2026-07-09 02:53:50 +05:00

quality-baseline.sh

Add curated quality-baseline corpus + auto-diff (#252 Phase 1) (#397)

2026-06-13 19:11:35 +05:00

quality-test.sh

fix(quality): precise benchlocal-cli source (sha/describe) — version is blind

2026-07-06 22:02:21 +00:00

rebench-full.sh

Re-gate beellama/gemma-dflash on the official pin; fix rebench-full n=3

2026-07-04 19:28:03 +00:00

rebench-report.py

fix(rebench-report): surface ceiling VRAM margin in verify-stress section (#184)

2026-05-24 20:05:52 +00:00

rebench-runtime.sh

rebench: add fail-fast verify-full preflight + fix runtime skip set (#306)

2026-06-03 21:00:16 +05:00

report.sh

fix(quality): precise benchlocal-cli source (sha/describe) — version is blind

2026-07-06 22:02:21 +00:00

setup-ai-studio.sh

setup-ai-studio.sh: make the "sign up then install the pipe" step unmissable (#510) (#527)

2026-06-30 00:08:52 +00:00

setup-image-studio.sh

studio: one-command setup-ai-studio.sh + auto-install the OWUI pipe

2026-06-24 03:47:18 +00:00

setup-video-studio.sh

studio: one-command setup-ai-studio.sh + auto-install the OWUI pipe

2026-06-24 03:47:18 +00:00

setup.sh

fix(launcher): GGUF verify-glob (#634) + .env engine-image passthrough (#632) (#639)

2026-07-08 12:52:47 +05:00

soak-helper.py

serve: neutral primary model name (qwen3.6-27b / gemma-4-31b), keep -autoround alias

2026-07-02 11:28:31 +00:00

soak-test.sh

Fix soak-test container auto-detect: match by engine port, not model allowlist (#405) (#414)

2026-06-15 07:07:26 +05:00

stream-toolcall-probe.py

serve: neutral primary model name (qwen3.6-27b / gemma-4-31b), keep -autoround alias

2026-07-02 11:28:31 +00:00

submit-bench.sh

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

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

switch.sh

preflight: warn on single-card GPU_MEMORY_UTILIZATION override above default (#641)

2026-07-08 23:18:33 +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

serve: neutral primary model name (qwen3.6-27b / gemma-4-31b), keep -autoround alias

2026-07-02 11:28:31 +00:00

verify-stress.sh

STRESS_FAST mode + honest dual-rig VRAM margins (dogfood findings)

2026-07-04 22:22:54 +00:00

verify.sh

serve: neutral primary model name (qwen3.6-27b / gemma-4-31b), keep -autoround alias

2026-07-02 11:28:31 +00:00