LICENSE
MANIFEST.in
README.md
pyproject.toml
setup.py
tests/test_gguf_download.py
tests/test_gguf_generation.py
tests/test_gguf_utils.py
tests/test_kernels.py
tests/test_multimodal_gguf.py
tests/test_plugin.py
vllm_gguf_plugin/__init__.py
vllm_gguf_plugin/config_parser.py
vllm_gguf_plugin/gguf_utils.py
vllm_gguf_plugin/loader.py
vllm_gguf_plugin/ops.py
vllm_gguf_plugin/plugin.py
vllm_gguf_plugin/weight_utils.py
vllm_gguf_plugin.egg-info/PKG-INFO
vllm_gguf_plugin.egg-info/SOURCES.txt
vllm_gguf_plugin.egg-info/dependency_links.txt
vllm_gguf_plugin.egg-info/entry_points.txt
vllm_gguf_plugin.egg-info/requires.txt
vllm_gguf_plugin.egg-info/top_level.txt
vllm_gguf_plugin/csrc/cuda_compat.h
vllm_gguf_plugin/csrc/dispatch_utils.h
vllm_gguf_plugin/csrc/torch_bindings.cpp
vllm_gguf_plugin/csrc/gguf/dequantize.cuh
vllm_gguf_plugin/csrc/gguf/ggml-common.h
vllm_gguf_plugin/csrc/gguf/gguf_kernel.cu
vllm_gguf_plugin/csrc/gguf/mmq.cuh
vllm_gguf_plugin/csrc/gguf/mmvq.cuh
vllm_gguf_plugin/csrc/gguf/moe.cuh
vllm_gguf_plugin/csrc/gguf/moe_vec.cuh
vllm_gguf_plugin/csrc/gguf/vecdotq.cuh
vllm_gguf_plugin/quantization/__init__.py
vllm_gguf_plugin/quantization/config.py
vllm_gguf_plugin/quantization/diffusion_config.py
vllm_gguf_plugin/quantization/fused_moe.py
vllm_gguf_plugin/quantization/linear.py
vllm_gguf_plugin/quantization/params.py
vllm_gguf_plugin/quantization/utils.py
vllm_gguf_plugin/quantization/vocal_embeds.py
vllm_gguf_plugin/triton/__init__.py
vllm_gguf_plugin/triton/dequantize/__init__.py
vllm_gguf_plugin/triton/dequantize/interface.py
vllm_gguf_plugin/triton/dequantize/utils.py
vllm_gguf_plugin/triton/dequantize/iq_quant/__init__.py
vllm_gguf_plugin/triton/dequantize/iq_quant/iq1_m.py
vllm_gguf_plugin/triton/dequantize/iq_quant/iq1_s.py
vllm_gguf_plugin/triton/dequantize/iq_quant/iq2_s.py
vllm_gguf_plugin/triton/dequantize/iq_quant/iq2_xs.py
vllm_gguf_plugin/triton/dequantize/iq_quant/iq2_xxs.py
vllm_gguf_plugin/triton/dequantize/iq_quant/iq3_s.py
vllm_gguf_plugin/triton/dequantize/iq_quant/iq3_xxs.py
vllm_gguf_plugin/triton/dequantize/iq_quant/iq4_nl.py
vllm_gguf_plugin/triton/dequantize/iq_quant/iq4_xs.py
vllm_gguf_plugin/triton/dequantize/k_quant/__init__.py
vllm_gguf_plugin/triton/dequantize/k_quant/q2_k.py
vllm_gguf_plugin/triton/dequantize/k_quant/q3_k.py
vllm_gguf_plugin/triton/dequantize/k_quant/q4_k.py
vllm_gguf_plugin/triton/dequantize/k_quant/q5_k.py
vllm_gguf_plugin/triton/dequantize/k_quant/q6_k.py
vllm_gguf_plugin/triton/dequantize/standard_quant/__init__.py
vllm_gguf_plugin/triton/dequantize/standard_quant/q4_0.py
vllm_gguf_plugin/triton/dequantize/standard_quant/q4_1.py
vllm_gguf_plugin/triton/dequantize/standard_quant/q5_0.py
vllm_gguf_plugin/triton/dequantize/standard_quant/q5_1.py
vllm_gguf_plugin/triton/dequantize/standard_quant/q8_0.py
vllm_gguf_plugin/triton/dequantize/standard_quant/q8_1.py
vllm_gguf_plugin/triton/fused_moe/__init__.py
vllm_gguf_plugin/triton/fused_moe/interface.py
vllm_gguf_plugin/triton/fused_moe/utils.py
vllm_gguf_plugin/triton/fused_moe/iq_quant/__init__.py
vllm_gguf_plugin/triton/fused_moe/iq_quant/iq1_m.py
vllm_gguf_plugin/triton/fused_moe/iq_quant/iq1_s.py
vllm_gguf_plugin/triton/fused_moe/iq_quant/iq2_s.py
vllm_gguf_plugin/triton/fused_moe/iq_quant/iq2_xs.py
vllm_gguf_plugin/triton/fused_moe/iq_quant/iq2_xxs.py
vllm_gguf_plugin/triton/fused_moe/iq_quant/iq3_s.py
vllm_gguf_plugin/triton/fused_moe/iq_quant/iq3_xxs.py
vllm_gguf_plugin/triton/fused_moe/iq_quant/iq4_nl.py
vllm_gguf_plugin/triton/fused_moe/iq_quant/iq4_xs.py
vllm_gguf_plugin/triton/fused_moe/k_quant/__init__.py
vllm_gguf_plugin/triton/fused_moe/k_quant/q2_k.py
vllm_gguf_plugin/triton/fused_moe/k_quant/q3_k.py
vllm_gguf_plugin/triton/fused_moe/k_quant/q4_k.py
vllm_gguf_plugin/triton/fused_moe/k_quant/q5_k.py
vllm_gguf_plugin/triton/fused_moe/k_quant/q6_k.py
vllm_gguf_plugin/triton/fused_moe/standard_quant/__init__.py
vllm_gguf_plugin/triton/fused_moe/standard_quant/q4_0.py
vllm_gguf_plugin/triton/fused_moe/standard_quant/q4_1.py
vllm_gguf_plugin/triton/fused_moe/standard_quant/q5_0.py
vllm_gguf_plugin/triton/fused_moe/standard_quant/q5_1.py
vllm_gguf_plugin/triton/fused_moe/standard_quant/q8_0.py
vllm_gguf_plugin/triton/fused_moe/standard_quant/q8_1.py
vllm_gguf_plugin/triton/gemm/__init__.py
vllm_gguf_plugin/triton/gemm/interface.py
vllm_gguf_plugin/triton/gemm/utils.py
vllm_gguf_plugin/triton/gemm/iq_quant/__init__.py
vllm_gguf_plugin/triton/gemm/iq_quant/iq1_m.py
vllm_gguf_plugin/triton/gemm/iq_quant/iq1_s.py
vllm_gguf_plugin/triton/gemm/iq_quant/iq2_s.py
vllm_gguf_plugin/triton/gemm/iq_quant/iq2_xs.py
vllm_gguf_plugin/triton/gemm/iq_quant/iq2_xxs.py
vllm_gguf_plugin/triton/gemm/iq_quant/iq3_s.py
vllm_gguf_plugin/triton/gemm/iq_quant/iq3_xxs.py
vllm_gguf_plugin/triton/gemm/iq_quant/iq4_nl.py
vllm_gguf_plugin/triton/gemm/iq_quant/iq4_xs.py
vllm_gguf_plugin/triton/gemm/iq_quant/iq_tables.py
vllm_gguf_plugin/triton/gemm/k_quant/__init__.py
vllm_gguf_plugin/triton/gemm/k_quant/q2_k.py
vllm_gguf_plugin/triton/gemm/k_quant/q3_k.py
vllm_gguf_plugin/triton/gemm/k_quant/q4_k.py
vllm_gguf_plugin/triton/gemm/k_quant/q5_k.py
vllm_gguf_plugin/triton/gemm/k_quant/q6_k.py
vllm_gguf_plugin/triton/gemm/standard_quant/__init__.py
vllm_gguf_plugin/triton/gemm/standard_quant/q4_0.py
vllm_gguf_plugin/triton/gemm/standard_quant/q4_1.py
vllm_gguf_plugin/triton/gemm/standard_quant/q5_0.py
vllm_gguf_plugin/triton/gemm/standard_quant/q5_1.py
vllm_gguf_plugin/triton/gemm/standard_quant/q8_0.py
vllm_gguf_plugin/triton/gemm/standard_quant/q8_1.py
vllm_gguf_plugin/weights_adapter/__init__.py
vllm_gguf_plugin/weights_adapter/base.py
vllm_gguf_plugin/weights_adapter/default.py
vllm_gguf_plugin/weights_adapter/gemma3.py
vllm_gguf_plugin/weights_adapter/diffusion/__init__.py
vllm_gguf_plugin/weights_adapter/diffusion/base.py
vllm_gguf_plugin/weights_adapter/diffusion/flux2_klein.py
vllm_gguf_plugin/weights_adapter/diffusion/integration.py
vllm_gguf_plugin/weights_adapter/diffusion/loader.py
vllm_gguf_plugin/weights_adapter/diffusion/qwen_image.py
vllm_gguf_plugin/weights_adapter/diffusion/z_image.py