Canonical SZL governed serve recipe: llama.cpp/Ollama CPU honest path for Khipu GGUF, schema validation outside the weights, energy MEASURED or UNAVAILABLE, GPU ROADMAP. Not a vLLM/TGI/TRT-LLM copy. Doctrine v11, Apache-2.0.
0
stars
8
commits
Python
primary language
Sep 8, 2026
updated
One OpenAI-shaped chat call. One pinned weight. One receipt.
KERNEL-owned canonical governed-inference recipe + validator + energy receipt for SZL Holdings.
This is not a vendor engine. It is the silhouette of 2026 serving (vLLM / SGLang / TGI / TensorRT-LLM / llama.cpp / Dynamo) — without copying those engines, and without fabricating tokens/s or joules.
Homepage: a-11-oy.com · Owner: Stephen P. Lutar Jr. / SZL Holdings · Doctrine v11 LOCKED 749/14/163 · Λ = Conjecture 1 (advisory, never a theorem) · Apache-2.0
elapsed_ms. No derived tok/s rating.szl-holdings/szl-forge / SZLHOLDINGS/szl-model-inference-lab. This KERNEL repo pins that MEASURED lab as the live CPU path. It does not invent a second runtime.szl-forge-lab. That Space is SNAPSHOT / READ-ONLY, not a trainer, not a serve runtime. Do not point szl-serve at forge-lab.Honesty plate: CARD.md.
Serve studio = SZLHOLDINGS/szl-model-inference-lab only. GPU remains ROADMAP.
| Surface | Class |
|---|---|
SZLHOLDINGS/szl-model-inference-lab | LIVE / MEASURED serve studio (this pin) |
SZLHOLDINGS/szl-forge-lab | SNAPSHOT, not a trainer, not a serve target |
| GPU / vLLM / TGI / TensorRT-LLM / SGLang / Dynamo | ROADMAP |
SZLHOLDINGS/energy-attested-runs | 8/8 SIMULATED — not this recipe's CPU energy evidence |
| Ask & Act | not a live control plane |
ATELIER serve studio. Not szl-forge-lab.
| Surface | https://szlholdings-szl-model-inference-lab.hf.space |
| Space | https://huggingface.co/spaces/SZLHOLDINGS/szl-model-inference-lab |
| FORGE source | https://github.com/szl-holdings/szl-forge/tree/main/spaces/szl-model-inference-lab |
| API | OpenAI subset POST /v1/chat/completions |
| Model | SZLHOLDINGS/SZL-Khipu-1.5B-GGUF@67d60ec577730747055491640cfb91fc4a4b5d25 |
| GGUF | SZL-Khipu-1.5B-Q4_K_M.gguf · SHA-256 13c1a1993063e1dff92f7413ccf48eaca6d48efc8801ae9af35961ae3396623a · 986047904 bytes |
| Sample 2026-08-28 | 21 completion tokens · elapsed_ms 2053 · execution_record UNSIGNED |
| Energy | joules=null · label UNAVAILABLE (CPU lab; MEASURED only from a real NVML delta) |
| SLA | Best-effort public demo. No provider SLA. Dummy bearer not-a-secret only — never a real token. |
curl https://szlholdings-szl-model-inference-lab.hf.space/v1/chat/completions \
-H "content-type: application/json" \
-H "authorization: Bearer not-a-secret" \
-d '{"model":"SZLHOLDINGS/SZL-Khipu-1.5B-GGUF@67d60ec577730747055491640cfb91fc4a4b5d25","messages":[{"role":"user","content":"Explain one limit of cryptographic receipts."}],"max_tokens":24,"stream":false}'
Contract: /.well-known/szl-inference-contract.json. Identity: /api/v1/identity.
Local llama.cpp and Ollama run the same Q4_K_M bytes. They are the airgap twin of the Space, not a clone of vLLM.
llama-cli -hf SZLHOLDINGS/SZL-Khipu-1.5B-GGUF:Q4_K_M
llama-server -hf SZLHOLDINGS/SZL-Khipu-1.5B-GGUF:Q4_K_M
ollama run hf.co/SZLHOLDINGS/SZL-Khipu-1.5B-GGUF:Q4_K_M
Print the recipe (no GGUF download):
python -m szl_serve recipe
Model output is proposal-only. Copy of khipu.schema.json is pinned from the GGUF repo (SHA-256 b95f9927366dae7c5d36cfb7de6e229eb605524318ab642a6aa2292a212170d0).
citedNodeIds → REJECT. Never silently repaired into a green plan.brainBinding.status stays NOT_RESOLVED.SYNTHETIC.REJECT).python -m szl_serve validate tests/fixtures/plan_model_proposed.json
python -m szl_serve validate tests/fixtures/plan_hallucinated_cited.json # exits 1
Each wrap uses szl-energy-attest semantics (import if available, else a tiny honest local meter):
| Energy | When |
|---|---|
| MEASURED | Real NVML energy-counter delta. joules is that number. |
| UNAVAILABLE | No GPU / no fresh NVML delta (the CPU lab and this CI). joules=null. |
Never invent a joule. Hash-chain a serve receipt: request hash, output hash, model pin, energy label. Receipt is UNSIGNED unless a key is actually present. Do not fake DSSE.
| Surface | Label |
|---|---|
| FORGE Space CPU OpenAI subset + GGUF pin + 2026-08-28 sample | MEASURED |
| llama.cpp / Ollama commands for the same pin | LIVE recipe (airgap twin) |
| Energy on CPU | UNAVAILABLE |
| GPU / vLLM / TGI / TensorRT-LLM / SGLang / Dynamo | ROADMAP |
| GPU attention | ROADMAP — no fused/paged-attention LIVE claim; no tokens/s invented |
SZLHOLDINGS/szl-forge-lab | SNAPSHOT — not a trainer; do not point this recipe at it |
SZLHOLDINGS/energy-attested-runs | 8/8 SIMULATED — not MEASURED NVML; not a live serve path |
| Ask & Act | not a live control plane |
| Chaski, ReceiptAgent weights | ROADMAP stubs on this config surface — not fake LIVE |
Λ is Conjecture 1. It does not become a theorem because a chat call returned 21 tokens.
Unit tests use fixture plan JSON. No network. Do not download the ~1 GB GGUF in CI.
pip install -e ".[test]"
pytest -q
LICENSE Apache-2.0, Copyright 2026 SZL Holdings
README.md this Series A face
CARD.md honesty plate
schemas/khipu.schema.json
szl_serve/{__init__,schema,energy,recipe,cli}.py
tests/fixtures/*.json
Governed AI you can pin — not a leaderboard you can fake.
a-11-oy.com · Khipu GGUF · MEASURED lab (FORGE)
SLSA: L1 honest · L2 attested · L3 roadmap. Λ = Conjecture 1. Trust ceiling 0.97 — never 100%.
8 commits
Python
100.0%
Canonical SZL governed serve recipe: llama.cpp/Ollama CPU honest path for Khipu GGUF, schema validation outside the weights, energy MEASURED or UNAVAILABLE, GPU ROADMAP. Not a vLLM/TGI/TRT-LLM copy. Doctrine v11, Apache-2.0.
0
stars
8
commits
Python
primary language
Sep 8, 2026
updated
One OpenAI-shaped chat call. One pinned weight. One receipt.
KERNEL-owned canonical governed-inference recipe + validator + energy receipt for SZL Holdings.
This is not a vendor engine. It is the silhouette of 2026 serving (vLLM / SGLang / TGI / TensorRT-LLM / llama.cpp / Dynamo) — without copying those engines, and without fabricating tokens/s or joules.
Homepage: a-11-oy.com · Owner: Stephen P. Lutar Jr. / SZL Holdings · Doctrine v11 LOCKED 749/14/163 · Λ = Conjecture 1 (advisory, never a theorem) · Apache-2.0
elapsed_ms. No derived tok/s rating.szl-holdings/szl-forge / SZLHOLDINGS/szl-model-inference-lab. This KERNEL repo pins that MEASURED lab as the live CPU path. It does not invent a second runtime.szl-forge-lab. That Space is SNAPSHOT / READ-ONLY, not a trainer, not a serve runtime. Do not point szl-serve at forge-lab.Honesty plate: CARD.md.
Serve studio = SZLHOLDINGS/szl-model-inference-lab only. GPU remains ROADMAP.
| Surface | Class |
|---|---|
SZLHOLDINGS/szl-model-inference-lab | LIVE / MEASURED serve studio (this pin) |
SZLHOLDINGS/szl-forge-lab | SNAPSHOT, not a trainer, not a serve target |
| GPU / vLLM / TGI / TensorRT-LLM / SGLang / Dynamo | ROADMAP |
SZLHOLDINGS/energy-attested-runs | 8/8 SIMULATED — not this recipe's CPU energy evidence |
| Ask & Act | not a live control plane |
ATELIER serve studio. Not szl-forge-lab.
| Surface | https://szlholdings-szl-model-inference-lab.hf.space |
| Space | https://huggingface.co/spaces/SZLHOLDINGS/szl-model-inference-lab |
| FORGE source | https://github.com/szl-holdings/szl-forge/tree/main/spaces/szl-model-inference-lab |
| API | OpenAI subset POST /v1/chat/completions |
| Model | SZLHOLDINGS/SZL-Khipu-1.5B-GGUF@67d60ec577730747055491640cfb91fc4a4b5d25 |
| GGUF | SZL-Khipu-1.5B-Q4_K_M.gguf · SHA-256 13c1a1993063e1dff92f7413ccf48eaca6d48efc8801ae9af35961ae3396623a · 986047904 bytes |
| Sample 2026-08-28 | 21 completion tokens · elapsed_ms 2053 · execution_record UNSIGNED |
| Energy | joules=null · label UNAVAILABLE (CPU lab; MEASURED only from a real NVML delta) |
| SLA | Best-effort public demo. No provider SLA. Dummy bearer not-a-secret only — never a real token. |
curl https://szlholdings-szl-model-inference-lab.hf.space/v1/chat/completions \
-H "content-type: application/json" \
-H "authorization: Bearer not-a-secret" \
-d '{"model":"SZLHOLDINGS/SZL-Khipu-1.5B-GGUF@67d60ec577730747055491640cfb91fc4a4b5d25","messages":[{"role":"user","content":"Explain one limit of cryptographic receipts."}],"max_tokens":24,"stream":false}'
Contract: /.well-known/szl-inference-contract.json. Identity: /api/v1/identity.
Local llama.cpp and Ollama run the same Q4_K_M bytes. They are the airgap twin of the Space, not a clone of vLLM.
llama-cli -hf SZLHOLDINGS/SZL-Khipu-1.5B-GGUF:Q4_K_M
llama-server -hf SZLHOLDINGS/SZL-Khipu-1.5B-GGUF:Q4_K_M
ollama run hf.co/SZLHOLDINGS/SZL-Khipu-1.5B-GGUF:Q4_K_M
Print the recipe (no GGUF download):
python -m szl_serve recipe
Model output is proposal-only. Copy of khipu.schema.json is pinned from the GGUF repo (SHA-256 b95f9927366dae7c5d36cfb7de6e229eb605524318ab642a6aa2292a212170d0).
citedNodeIds → REJECT. Never silently repaired into a green plan.brainBinding.status stays NOT_RESOLVED.SYNTHETIC.REJECT).python -m szl_serve validate tests/fixtures/plan_model_proposed.json
python -m szl_serve validate tests/fixtures/plan_hallucinated_cited.json # exits 1
Each wrap uses szl-energy-attest semantics (import if available, else a tiny honest local meter):
| Energy | When |
|---|---|
| MEASURED | Real NVML energy-counter delta. joules is that number. |
| UNAVAILABLE | No GPU / no fresh NVML delta (the CPU lab and this CI). joules=null. |
Never invent a joule. Hash-chain a serve receipt: request hash, output hash, model pin, energy label. Receipt is UNSIGNED unless a key is actually present. Do not fake DSSE.
| Surface | Label |
|---|---|
| FORGE Space CPU OpenAI subset + GGUF pin + 2026-08-28 sample | MEASURED |
| llama.cpp / Ollama commands for the same pin | LIVE recipe (airgap twin) |
| Energy on CPU | UNAVAILABLE |
| GPU / vLLM / TGI / TensorRT-LLM / SGLang / Dynamo | ROADMAP |
| GPU attention | ROADMAP — no fused/paged-attention LIVE claim; no tokens/s invented |
SZLHOLDINGS/szl-forge-lab | SNAPSHOT — not a trainer; do not point this recipe at it |
SZLHOLDINGS/energy-attested-runs | 8/8 SIMULATED — not MEASURED NVML; not a live serve path |
| Ask & Act | not a live control plane |
| Chaski, ReceiptAgent weights | ROADMAP stubs on this config surface — not fake LIVE |
Λ is Conjecture 1. It does not become a theorem because a chat call returned 21 tokens.
Unit tests use fixture plan JSON. No network. Do not download the ~1 GB GGUF in CI.
pip install -e ".[test]"
pytest -q
LICENSE Apache-2.0, Copyright 2026 SZL Holdings
README.md this Series A face
CARD.md honesty plate
schemas/khipu.schema.json
szl_serve/{__init__,schema,energy,recipe,cli}.py
tests/fixtures/*.json
Governed AI you can pin — not a leaderboard you can fake.
a-11-oy.com · Khipu GGUF · MEASURED lab (FORGE)
SLSA: L1 honest · L2 attested · L3 roadmap. Λ = Conjecture 1. Trust ceiling 0.97 — never 100%.
8 commits
Python
100.0%