BGE Large English v1.5

Encoder: kv_cache_bytes_per_token = 0, formula does not apply (single bidirectional forward pass, no cache). hidden_size 1024 fixes the output at 1024 dims = 4 KB fp32 per document; 24 layers is the depth that costs real time. This is the last BERT-geometry BGE and it is 3x the compute of bge-base for a quality gain that saturates — flops_per_token_active 6.70e8 vs 2.19e8, and at 512 tokens that is ~0.69 GFLOP per query. The 335142400 total is IDENTICAL to thenlper/gte-large, which is expected: both are BERT-large with vocab 30522, hidden 1024, 24 layers, intermediate 4096, 16 heads. Two different training runs of the same shape. 512 max_position_embeddings — the hard ceiling that pushed the field to bge-m3 and jina-v3. MIT. GGUF (CompendiumLabs, mradermacher) and ONNX (Qdrant onnx-Q, castorini) both exist. 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=bi-encoder. REQUIRED KERNEL CLASS: a single full-sequence bidirectional forward pass with a pooling reduction. No KV cache, no incremental state, no autoregressive weight streaming - flop/embedding-batch-encoding gives AI = B*t flop/byte (weights read once for all B documents), so on H100 SXM at ridge 295.4 a single 128-token encode at B=1 is memory-bound but at B=3 it is compute-bound, and the threshold is the PRODUCT B*t. flop/cross-encoder-reranking makes the same point for the scoring phase. This inverts the hardware-selection rule: an embedding/rerank tier wants FLOPS and core count, not HBM bandwidth. SUPPORTED BY (cited): vLLM pooling is a separate runner with its own endpoint surface and the broadest architecture table in the repo - BertModel, BgeM3EmbeddingModel, GteModel, JteNewModel (mGTE-TRM), JinaEmbeddingsV5Model, LlamaBidirectionalModel, LlamaModel/MistralModel (intfloat/e5-mistral-7b-instruct), ModernBertModel, NomicBertModel, Qwen2Model, Qwen3Model, RobertaModel, XLMRobertaModel, plus any generative model via automatic --convert, with the Transformers modeling backend covering encoder-only architectures directly [[vllm-pooling-models]]. TEI is the purpose-built reference and lists BERT, CamemBERT, XLM-RoBERTa, NomicBERT, JinaBERT (Alibi), MPNet, ModernBERT plus RoPE decoder backbones Mistral, Alibaba GTE, Qwen2, Qwen3 and Gemma3 [[hf-text-embeddings-inference]]. SGLang's embedding page states native encoder architectures are auto-detected while decoder-style embedders need --is-embedding, and that on CUDA it automatically uses breakable CUDA graph for the full encoder prefill and DISABLES radix-cache and chunked-prefill [[mdl2-sglang-embedding-rerank-models]]. sentence-transformers covers everything transformers can load [[sentence-transformers]]. llama.cpp reaches BERT-family encoders via the LLM_ARCH_BERT / MODERN_BERT / NOMIC_BERT / JINA_BERT_V2 / JINA_BERT_V3 entries [[pap-arch-llamacpp-arch-registry]]. CORRECTNESS CAVEATS THAT ARE ARCHITECTURE-SPECIFIC AND CITED: vLLM's pooling path is a capability not a speed win - the project's own docs say 'We currently support pooling models primarily for convenience. This is not guaranteed to provide any performance improvements over using Hugging Face Transformers or Sentence Transformers directly' [[vllm-pooling-models]]. Several of the architectures above need --trust-remote-code or --hf-overrides, so 'supported' sometimes means 'supported after three flags' [[vllm-pooling-models]]. bge-m3 ships extra sparse AND ColBERT weights with a separate docs path, and jina-embeddings-v3 is limited to text-matching with LoRA merged rather than selected [[vllm-pooling-models]]. TEI's --dtype accepts only float16 and float32 - no int8 or fp8 at runtime, so quantization must happen at export [[hf-text-embeddings-inference]]. llama.cpp's embedding path cannot serve SPLADE/learned-sparse encoders, cannot serve ColBERT end to end, and cannot serve multimodal encoders requiring a projector graph [[llama-cpp-embedding-server]]. For the Qwen2-decoder-as-bi-encoder pattern specifically, both gte-Qwen2 and Qwen2 family models are the documented --trust-remote-code case in vLLM [[vllm-pooling-models]].