From ff8dfed498de1512393d3b9c3d54c20929c33586 Mon Sep 17 00:00:00 2001 From: Vuong Hoang Date: Mon, 14 Sep 2026 09:11:07 -0700 Subject: [PATCH] =?UTF-8?q?docs(fv-ml1):=20regenerate=20seat=20inventory?= =?UTF-8?q?=20=E2=80=94=20cyberprev=20in=20the=20sec=20seat,=20mog-sec=20g?= =?UTF-8?q?one?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Live-read regeneration after promoting cyberprev into sec/sec-reasoning and retiring mog-sec. GPU0 now carries cyberprev alone; sec/sec-reasoning aliases resolve to :8025. --- docs/pfi/fv-ml1-gpu-seat-inventory.md | 55 +++++++++------------------ 1 file changed, 18 insertions(+), 37 deletions(-) diff --git a/docs/pfi/fv-ml1-gpu-seat-inventory.md b/docs/pfi/fv-ml1-gpu-seat-inventory.md index f452747..444350d 100644 --- a/docs/pfi/fv-ml1-gpu-seat-inventory.md +++ b/docs/pfi/fv-ml1-gpu-seat-inventory.md @@ -6,7 +6,7 @@ Hand-edits are overwritten and, worse, drift silently while looking authoritative — which is exactly the failure this file replaced. --> -**Generated 2026-09-14 06:00 UTC** by `scripts/seat-inventory.py`, read from the running +**Generated 2026-09-14 16:10 UTC** by `scripts/seat-inventory.py`, read from the running containers on `100.64.0.7` — `docker inspect`, `nvidia-smi`, each model's own `config.json`, and the `.PROVENANCE.txt` siblings on `/tank`. @@ -17,15 +17,14 @@ containers on `100.64.0.7` — `docker inspect`, `nvidia-smi`, each model's own | GPU | seat | VRAM | weights | KV tokens | ctx | concurrency | util | |---|---|---|---|---|---|---|---| -| 0 | `vllm-mog-sec` | 46.6 GiB | 25.47 GiB | 342,920 | 163840 | **2.09×** | 0.50 | -| 0 | `vllm-gen` | 38.3 GiB | 21.97 GiB | 268,205 | 262144 | **1.02×** | 0.38 | +| 0 | `vllm-cyberprev` | 38.0 GiB | 25.11 GiB | 166,264 | 163840 | **1.01×** | 0.40 | | 1 | `vllm-meromero-rp` | 37.9 GiB | 19.51 GiB | 266,334 | 262144 | **1.02×** | 0.40 | | 1 | `vllm-erp-seat` | 26.3 GiB | 15.9 GiB | 534,649 | 262144 | **2.04×** | 0.30 | | 1 | `vllm-reward` | 9.0 GiB | 4.41 GiB | 26,224 | 16384 | **1.60×** | 0.10 | | 1 | `vllm-coder` | 6.0 GiB | 2.98 GiB | 112,624 | 8192 | **13.75×** | 0.06 | | 1 | `vllm-embed` | 3.4 GiB | 1.12 GiB | 10,272 | 8192 | **1.25×** | 0.03 | | 1 | `vllm-rerank-a3` | 2.1 GiB | 1.06 GiB | — | 8192 | — | 0.03 | -| 2 | `vllm-flash-next` | 94.7 GiB | 79.44 GiB | 344,155 | 262144 | **1.31×** | 0.96 | +| 2 | `vllm-flash-next` | 93.1 GiB | 76.82 GiB | 344,155 | 262144 | **1.31×** | 0.96 | **Concurrency** = KV tokens ÷ context: how many full-length requests fit at once. Below ~1.0× the seat cannot hold even one conversation at its declared @@ -33,32 +32,14 @@ context. ## Lineage and quantization -### `vllm-gen` — GPU 0 +### `vllm-cyberprev` — GPU 0 -- **serves:** `qwen3.8-27b-uncensored`, `qwen3.8-27b-uncensored-thinking` -- **model:** `/tank/aimodels/qwen38-27b-orcarouter-nvfp4-mixed` -- **architecture:** Qwen3_5ForConditionalGeneration (qwen3_5), 64 layers -- **quantization:** compressed-tensors / mixed-precision — W8A8 (float-quantized), W4A4 (nvfp4-pack-quantized) -- **speculative decoding:** `{"method": "qwen3_5_mtp", "num_speculative_tokens": 3}` -- **image:** `vllm/vllm-openai:nightly-311b3513af33bc29b4acb2fde2e9313e5e9966a0` - -### `vllm-mog-sec` — GPU 0 - -- **serves:** `mog-sec-27b`, `mog-sec-27b-thinking` -- **model:** `/tank/aimodels/mog-sec-27b-nvfp4-mixed` +- **serves:** `cyberprev-27b`, `cyberprev-27b-thinking` +- **model:** `/tank/aimodels/cyberprev-nvfp4-mixed-v2` - **architecture:** Qwen3_5ForConditionalGeneration (qwen3_5), 64 layers - **quantization:** compressed-tensors / mixed-precision — W8A8 (float-quantized), W4A4 (nvfp4-pack-quantized) - **speculative decoding:** `{"method": "dflash", "model": "/drafter", "num_speculative_tokens": 7}` - **image:** `vllm/vllm-openai:nightly-e9d1398d9edfd90fcc1cf783805240e3effec013` -- **provenance:** - ``` - model: Blackfrost-Research/M.O.G.-SEC-27B-1M-CTX-BF16 (bf16, pen-test seat source) - source_url: https://huggingface.co/Blackfrost-Research/M.O.G.-SEC-27B-1M-CTX-BF16 - revision_pinned: deede67794b4eaaf31f016d02a0aaf71f1a303b9 - pulled_by: infra-ops (as llmuser) - pulled_at_utc: 2026-08-21T09:10Z - size_on_disk: 52 GB (18 shards, index total_size 55.6 GB) - ``` ### `vllm-coder` — GPU 1 @@ -105,9 +86,9 @@ context. ### `vllm-flash-next` — GPU 2 - **serves:** `qwen3.8-flash-next-uncensored`, `qwen3.8-flash-next-uncensored-thinking` -- **model:** `/tank/aimodels/qwen38-flash-next-abliterated-nvfp4` +- **model:** `/tank/aimodels/qwen38-flash-next-orcarouter-nvfp4-plefp8` - **architecture:** Qwen4ExpForConditionalGeneration (qwen4_exp), 48 layers, 512 experts -- **quantization:** modelopt / None — W4A4 (None) +- **quantization:** compressed-tensors / mixed-precision — W8A16 (naive-quantized), W4A16 (nvfp4-pack-quantized) - **speculative decoding:** `{"method": "mtp", "num_speculative_tokens": 3}` - **image:** `vllm/vllm-openai:nightly-eed1f3d0c6043bd494424a22443ee198dd56f657` @@ -120,22 +101,22 @@ context. | `char-rp` | 8016 | | `char-rp-fast` | 8021 | | `char-rp-reasoning` | 8016 | -| `chat-judge` | 8015 | -| `classifier` | 8015 | +| `chat-judge` | 8022 | +| `classifier` | 8022 | | `coder-fast` | 8020 | | `erp-tune-v2` | 8098 | | `gemma4-26b-a4b-it-base` | 8099 | -| `gen` | 8015 | +| `gen` | 8022 | | `gen-large` | 8022 | -| `gen-reasoning` | 8015 | -| `image-judge` | 8015 | -| `qwen-image-bench` | 8015 | +| `gen-reasoning` | 8022 | +| `image-judge` | 8022 | +| `qwen-image-bench` | 8022 | | `qwen3-embedding` | 8001 | | `reranker` | 8013 | -| `sec` | 8019 | -| `sec-reasoning` | 8019 | -| `summarizer` | 8015 | -| `summarizer-large` | 8015 | +| `sec` | 8025 | +| `sec-reasoning` | 8025 | +| `summarizer` | 8022 | +| `summarizer-large` | 8022 | ---