OpenR1-Qwen-7B

CONTEXT SCALING: null is a VERIFIED value, checked against config rather than left blank. config.json declares rope_scaling null, rope_theta 300000, max_position_embeddings 32768. Config is byte-for-byte the same shape as OpenThinker3-7B and Bespoke-Stratos-7B (Qwen2ForCausalLM, 3584 hidden, 28 layers, 28/4 heads), confirming the Open-R1 pipeline output is architecturally the Qwen2.5-7B base. The open-r1 org's larger checkpoints (OpenR1-Math-220B etc.) were not machine-verifiable from this network - config fetches returned HTTP 401 - so no record is created for them. head_dim derived as 3584 / 28 = 128; gqa_ratio = 7.KV bytes/token at bf16 (2 bytes/element): 28 layers x 4 KV heads x 128 head_dim x 2 (K and V) x 2 bytes = 57344 B/token = 56.0 KiB/token. context_scaling is null: context length is native to the pretrained config, no rope_scaling. SERVICEABILITY JOIN (added 2026-10-03; the architecture x engine matrix this record was missing, with a citation per cell in docs/13-model-compatibility.md): FAMILY=dense-gqa. REQUIRED KERNEL CLASS: ordinary causal attention plus GEMM/GEMV. This is the baseline every engine in this repo implements, so the join here is a floor rather than a filter: no engine record in data/engines/ states that dense GQA is unsupported. SUPPORTED BY (cited): vLLM LlamaForCausalLM / Qwen2 / Qwen3 / Mistral / Phi3ForCausalLM rows [[mdl2-vllm-supported-models-2026-10]]; TensorRT-LLM LlamaForCausalLM, Qwen2ForCausalLM, Qwen3ForCausalLM, Phi3ForCausalLM rows [[mdl2-trtllm-supported-models]]; SGLang generative table (Llama, Qwen, Mistral families) [[mdl2-sglang-generative-models]]; llama.cpp LLM_ARCH_LLAMA [[pap-arch-llamacpp-arch-registry]]. HARD CONSTRAINTS THAT DO APPLY even to dense GQA, and they are model-shape rather than architecture-class: tensor-parallel size must divide the attention head count or the engine refuses to start [[mgpu-tp-size-must-divide-attention-heads]] (affects vllm and sglang); and a GQA KV cache is the thing paged-attention machinery exists for, so an engine with no paged KV (llama.cpp's slot-based pool [[llama-cpp]], exllamav2 [[exllamav2]]) loses the concurrency lever rather than the ability to run. ONE HARDWARE-DEPENDENT KERNEL GATE THAT IS NOT ABOUT GQA: on RDNA, vLLM's custom paged-attention kernel is gated on head_size == 128 AND block_size == 16, so a dense GQA model with head_dim 256 falls to the Triton 2D fallback and decode falls off a cliff - measured 12.1 tok/s at 518 tokens of context to 4.2 tok/s at 32k, with kernel_paged_attention_2d growing 28.3x [[rdna-triton-paged-attn-decode-cliff]]. Check head_dim before blaming the card.