{"slug":"ds4-vision-2x6000-kk-dspark-k3","title":"DeepSeek V4 Flash Vision on 2x RTX PRO 6000 Blackwell \u2014 Karmic Kraken TP2 DSpark K3","summary":"Karmic Kraken TP2 vision-capable serving recipe: DSpark K3, image-aware prefix-cache checks passed.","license":"CC-BY-4.0","tier":"community","beta":true,"revision":{"no":2,"commit_sha":"8aaf942be9a0e838a483ebc0f9817710bedebedf","content_hash":"53912a3ff23f8b7a61a3c16f9ef3dff127df225a","created_at":"2026-10-20 21:54:52.661047-06","notes":"Benchmark-qualified configuration from local-inference-lab/rtx6kpro (Karmic Kraken serving report). Five warmed 30-second windows per cell on RTX PRO 6000 Blackwell Max-Q; decode ctx-0 temp 1. Launch argv transcribed verbatim from the repo's unified Docker guide (same composition). Measured: C1 193.9 tok/s, 32K prefill 9182 tok/s."},"engine_source":{"type":"docker_image","git_url":"https://github.com/local-inference-lab/vllm","base_engine":"vllm","pip_package":null,"base_version":"karmic-kraken-beta (vLLM cfdecfaa4)","image_digest":"ghcr.io/local-inference-lab/vllm:karmic-kraken-beta-20260922-3221ccacf71002ea","install_note":null,"pinned_commit":"cfdecfaa4739ee3141c9745997cd8a83f31745a4"},"credit":[{"name":"local-inference-lab","url":"https://github.com/local-inference-lab/rtx6kpro"}],"author":{"name":"localai-recipes","isSite":true},"uploaded_by":"localai-recipes","config":{"launch":["serve","deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","--async-scheduling","--attention-backend","B12X","--block-size","256","--code-revision","6821d6ad3681a4b137b066b76094fa82ebd0a380","--compilation-config","'{\"cudagraph_mode\":\"FULL_AND_PIECEWISE\",\"custom_ops\":[\"all\"]}'","--decode-context-parallel-size","1","--default-chat-template-kwargs","'{\"thinking\":true,\"reasoning_effort\":\"high\"}'","--dtype","bfloat16","--enable-auto-tool-choice","--enable-chunked-prefill","--enable-flashinfer-autotune","--enable-force-include-usage","--enable-prefix-caching","--enable-prompt-tokens-details","--enable-request-id-headers","--gpu-memory-utilization","0.975","--host","0.0.0.0","--kv-cache-dtype","fp8","--load-format","instanttensor","--max-cudagraph-capture-size","16","--max-model-len","-1","--max-num-batched-tokens","4096","--max-num-seqs","4","--moe-backend","b12x","--override-generation-config","'{\"temperature\":1.0,\"top_p\":0.95}'","--pipeline-parallel-size","1","--port","8000","--prefix-cache-retention-interval","4096","--reasoning-parser","deepseek_v4","--revision","6821d6ad3681a4b137b066b76094fa82ebd0a380","--no-scheduler-reserve-full-isl","--served-model-name","DeepSeek-V4-Flash-Vision-Exp","--speculative-config","'{\"method\":\"dspark\",\"draft_sample_method\":\"probabilistic\",\"rejection_sample_method\":\"standard\",\"num_speculative_tokens\":3,\"model\":\"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp\",\"revision\":\"6821d6ad3681a4b137b066b76094fa82ebd0a380\"}'","--tensor-parallel-size","2","--tokenizer-mode","deepseek_v4","--tool-call-parser","deepseek_v4","--trust-remote-code"]},"models":[{"slug":"deepseek-v4-flash-vision-exp","name":"DeepSeek-V4-Flash-Vision-Exp","hf_repo":"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","quant":null}],"hardware":[{"slug":"nvidia-rtx-pro-6000-blackwell-max-qx2","vendor":"nvidia","card":"RTX PRO 6000 Blackwell Max-Q","card_family":"rtx-pro-6000-blackwell","vram_gb":96,"device_count":2}],"generation":"blackwell","tags":["dspark"],"tasks":["chat","code","vision"],"aa":{"aa_index":35,"aa_provenance":"published","aa_source_url":"https://artificialanalysis.ai/models/deepseek-v4-flash-vision","aa_index_version":null,"aa_methodology_version":"v4.3.2","aa_published_fetched_at":"2026-10-06 18:30:00-06","aa_family_slug":"deepseek-v4-flash-vision-exp","aa_resolved_slug":"deepseek-v4-flash-vision-exp"},"performance":null,"perf_points":[],"agent":{"prompt":"Fetch https://localairecipes.com/api/v1/recipes/ds4-vision-2x6000-kk-dspark-k3.json and apply the inference recipe it describes (engine flags, model, quant, context) to my setup. Ask before overwriting any existing config.","curl":"curl -fsSL https://localairecipes.com/api/v1/recipes/ds4-vision-2x6000-kk-dspark-k3.json"},"requirements":{"requires":["Docker (or a compatible OCI container runtime)","NVIDIA Container Toolkit (nvidia-container-toolkit) - exposes host GPUs to the container"],"driver_floor":{"cuda":null,"linux_min":null,"text":"unknown - check the image tag","source":"NVIDIA CUDA Toolkit Release Notes - driver compatibility tables (https://docs.nvidia.com/cuda/cuda-toolkit-release-notes/, fetched 2026-10-03)"},"placeholders":["Hardware-bound values in this recipe (device counts, bind-mount paths, utilization, ports) describe the author's machine, not yours - map them to your own rig before launching. Keep the engine flags, model, quant, and parallelism strategy; adjust paths and ports to the hardware you actually have.","GPU identity: list your GPUs with `nvidia-smi -L` and substitute your own GPU UUIDs/indices wherever the recipe pins the author's.","Model directory: bind-mount paths are author-side - point them at your own mount where the model files live.","Host port: pick a free port on your machine and publish the container there; keep the in-container port unchanged."]},"artifacts":[],"links":{"self":"/api/v1/recipes/ds4-vision-2x6000-kk-dspark-k3.json","alternate":"/r/ds4-vision-2x6000-kk-dspark-k3","describedby":"/openapi.json"},"updated_at":"2026-10-20 21:54:52.661047-06","created_at":"2026-10-20 21:49:13.002514-06","speeds":{"decode_tok_s":0,"prefill_tok_s":0,"leaderboard":"/api/v1/leaderboard.json"}}