LICENSE
README.md
pyproject.toml
forge/__init__.py
forge/__main__.py
forge/dispatcher.py
forge/gliner_postprocessor.py
forge/gliner_preprocessor.py
forge/model_prep.py
forge/multi_instance.py
forge/preflight.py
forge/processor_base.py
forge/registration.py
forge/serve_cli.py
forge/server.py
forge/validate_plugins.py
forge/_deprecated/cli.py
forge/_deprecated/config_utils.py
forge/_deprecated/plugin_base.py
forge/_deprecated/pooler_base.py
forge/_deprecated/registry.py
forge/_deprecated/weight_utils.py
forge/patches/__init__.py
forge/testing/__init__.py
forge/testing/harness.py
kernels/__init__.py
kernels/ff_fused.py
kernels/flash_attention_rpb.py
kernels/flash_deberta_attention.py
kernels/flash_t5gemma2_attention.py
kernels/fused_dropout_residual.py
kernels/fused_embed_scale_eoi.py
kernels/fused_gemma_rms_norm_dropout_residual.py
kernels/fused_glu_mlp.py
kernels/fused_layernorm.py
kernels/fused_qk_norm_rope.py
kernels/fused_rope_global.py
kernels/fused_rope_local.py
kernels/tests/__init__.py
kernels/tests/test_fused_gemma_rms_norm_dropout_residual.py
models/__init__.py
models/deberta/__init__.py
models/deberta/config.py
models/deberta/deberta_encoder.py
models/deberta/parity_test.py
models/deberta_v2/__init__.py
models/deberta_v2/config.py
models/deberta_v2/deberta_v2_encoder.py
models/deberta_v2/parity_test.py
models/modernbert/__init__.py
models/modernbert/config.py
models/modernbert/modernbert_encoder.py
models/mt5/__init__.py
models/mt5/config.py
models/mt5/mt5_encoder.py
models/t5gemma2/__init__.py
models/t5gemma2/config.py
models/t5gemma2/kernel_benchmark.py
models/t5gemma2/parity_test.py
models/t5gemma2/t5gemma2_encoder.py
models/t5gemma2/t5gemma2_model.py
models/t5gemma2/throughput_benchmark.py
plugins/collfm2/__init__.py
plugins/collfm2/benchmark.py
plugins/collfm2/config.py
plugins/collfm2/generate_reference.py
plugins/collfm2/io_processor.py
plugins/collfm2/model.py
plugins/collfm2/parity_test.py
plugins/collfm2/pooler.py
plugins/collfm2/processor.py
plugins/collfm2/serve.py
plugins/collfm2/setup.py
plugins/colqwen3/__init__.py
plugins/colqwen3/benchmark.py
plugins/colqwen3/config.py
plugins/colqwen3/generate_reference.py
plugins/colqwen3/io_processor.py
plugins/colqwen3/model.py
plugins/colqwen3/parity_test.py
plugins/colqwen3/pooler.py
plugins/colqwen3/processor.py
plugins/colqwen3/serve.py
plugins/colqwen3/setup.py
plugins/deberta_gliner/__init__.py
plugins/deberta_gliner/benchmark.py
plugins/deberta_gliner/config.py
plugins/deberta_gliner/io_processor.py
plugins/deberta_gliner/model.py
plugins/deberta_gliner/parity_test.py
plugins/deberta_gliner/pooler.py
plugins/deberta_gliner/processor.py
plugins/deberta_gliner/setup.py
plugins/deberta_gliner2/__init__.py
plugins/deberta_gliner2/benchmark.py
plugins/deberta_gliner2/config.py
plugins/deberta_gliner2/io_processor.py
plugins/deberta_gliner2/model.py
plugins/deberta_gliner2/parity_test.py
plugins/deberta_gliner2/processor.py
plugins/deberta_gliner2/setup.py
plugins/deberta_gliner_linker/__init__.py
plugins/deberta_gliner_linker/benchmark.py
plugins/deberta_gliner_linker/config.py
plugins/deberta_gliner_linker/io_processor.py
plugins/deberta_gliner_linker/model.py
plugins/deberta_gliner_linker/pooler.py
plugins/deberta_gliner_linker/processor.py
plugins/deberta_gliner_linker/setup.py
plugins/deberta_gliner_linker/vllm_pooling_attention_mask.py
plugins/embeddinggemma/__init__.py
plugins/embeddinggemma/benchmark.py
plugins/embeddinggemma/config.py
plugins/embeddinggemma/io_processor.py
plugins/embeddinggemma/model.py
plugins/embeddinggemma/parity_test.py
plugins/embeddinggemma/pooler.py
plugins/embeddinggemma/processor.py
plugins/embeddinggemma/setup.py
plugins/lfm2_colbert/__init__.py
plugins/lfm2_colbert/benchmark.py
plugins/lfm2_colbert/config.py
plugins/lfm2_colbert/io_processor.py
plugins/lfm2_colbert/model.py
plugins/lfm2_colbert/parity_test.py
plugins/lfm2_colbert/setup.py
plugins/mmbert_gliner/__init__.py
plugins/mmbert_gliner/benchmark.py
plugins/mmbert_gliner/config.py
plugins/mmbert_gliner/io_processor.py
plugins/mmbert_gliner/model.py
plugins/mmbert_gliner/parity_test.py
plugins/mmbert_gliner/pooler.py
plugins/mmbert_gliner/processor.py
plugins/mmbert_gliner/setup.py
plugins/modernbert_gliner_rerank/__init__.py
plugins/modernbert_gliner_rerank/config.py
plugins/modernbert_gliner_rerank/io_processor.py
plugins/modernbert_gliner_rerank/model.py
plugins/modernbert_gliner_rerank/pooler.py
plugins/modernbert_gliner_rerank/processor.py
plugins/moderncolbert/__init__.py
plugins/moderncolbert/benchmark.py
plugins/moderncolbert/config.py
plugins/moderncolbert/generate_reference.py
plugins/moderncolbert/io_processor.py
plugins/moderncolbert/model.py
plugins/moderncolbert/parity_test.py
plugins/moderncolbert/pooler.py
plugins/moderncolbert/processor.py
plugins/moderncolbert/serve.py
plugins/moderncolbert/setup.py
plugins/mt5_gliner/__init__.py
plugins/mt5_gliner/benchmark.py
plugins/mt5_gliner/config.py
plugins/mt5_gliner/io_processor.py
plugins/mt5_gliner/model.py
plugins/mt5_gliner/parity_test.py
plugins/mt5_gliner/pooler.py
plugins/mt5_gliner/processor.py
plugins/mt5_gliner/setup.py
plugins/nemotron_colembed/__init__.py
plugins/nemotron_colembed/benchmark.py
plugins/nemotron_colembed/config.py
plugins/nemotron_colembed/io_processor.py
plugins/nemotron_colembed/model.py
plugins/nemotron_colembed/parity_test.py
plugins/nemotron_colembed/setup.py
poolers/__init__.py
poolers/colbert.py
poolers/colpali.py
poolers/gliner.py
poolers/gliner2.py
vllm_factory/__init__.py
vllm_factory.egg-info/PKG-INFO
vllm_factory.egg-info/SOURCES.txt
vllm_factory.egg-info/dependency_links.txt
vllm_factory.egg-info/entry_points.txt
vllm_factory.egg-info/requires.txt
vllm_factory.egg-info/top_level.txt
vllm_factory/api/__init__.py
vllm_factory/api/request_models.py
vllm_factory/api/response_models.py
vllm_factory/compat/__init__.py
vllm_factory/compat/__main__.py
vllm_factory/compat/attention_mask_compat.py
vllm_factory/compat/bridges.py
vllm_factory/compat/doctor.py
vllm_factory/compat/vllm_capabilities.py
vllm_factory/compat/vllm_imports.py
vllm_factory/composable/__init__.py
vllm_factory/composable/backbone_registry.py
vllm_factory/composable/io_processor.py
vllm_factory/composable/model.py
vllm_factory/composable/pooler_registry.py
vllm_factory/io/__init__.py
vllm_factory/io/base.py
vllm_factory/pooling/__init__.py
vllm_factory/pooling/adapters.py
vllm_factory/pooling/context.py
vllm_factory/pooling/protocol.py
vllm_factory/pooling/vllm_adapter.py
vllm_factory/registry/__init__.py
vllm_factory/registry/general_plugins.py
vllm_factory/registry/io_processor_plugins.py
vllm_factory/registry/verification.py