LICENSE
MANIFEST.in
README.md
pyproject.toml
requirements.txt
setup.py
tests/__init__.py
tests/test_base.py
tests/test_quantization.py
tests/test_tpu_info.py
tests/test_utils.py
tests/tpu_backend_test.py
tests/core/__init__.py
tests/core/test_adapters.py
tests/core/test_core_tpu.py
tests/core/test_disagg_executor.py
tests/core/test_disagg_utils.py
tests/core/test_init.py
tests/kernels/__init__.py
tests/kernels/quantized_matmul_kernel_test.py
tests/kernels/ragged_kv_cache_update_v2_test.py
tests/kernels/ragged_paged_attention_kernel_v2_test.py
tests/kernels/ragged_paged_attention_kernel_v3_test.py
tests/lora/__init__.py
tests/lora/test_lora.py
tpu_inference/__init__.py
tpu_inference/backend.py
tpu_inference/logger.py
tpu_inference/tpu_info.py
tpu_inference/utils.py
tpu_inference.egg-info/PKG-INFO
tpu_inference.egg-info/SOURCES.txt
tpu_inference.egg-info/dependency_links.txt
tpu_inference.egg-info/requires.txt
tpu_inference.egg-info/top_level.txt
tpu_inference/adapters/__init__.py
tpu_inference/adapters/vllm_adapters.py
tpu_inference/adapters/vllm_config_adapters.py
tpu_inference/core/__init__.py
tpu_inference/core/adapters.py
tpu_inference/core/core_tpu.py
tpu_inference/core/disagg_executor.py
tpu_inference/core/disagg_utils.py
tpu_inference/di/__init__.py
tpu_inference/di/abstracts.py
tpu_inference/di/host.py
tpu_inference/di/interfaces.py
tpu_inference/distributed/__init__.py
tpu_inference/distributed/tpu_connector.py
tpu_inference/distributed/utils.py
tpu_inference/executors/__init__.py
tpu_inference/executors/ray_distributed_executor.py
tpu_inference/experimental/__init__.py
tpu_inference/experimental/llama3_jax_stashed.py
tpu_inference/interfaces/__init__.py
tpu_inference/interfaces/cache.py
tpu_inference/interfaces/config.py
tpu_inference/interfaces/config_parts.py
tpu_inference/interfaces/engine.py
tpu_inference/interfaces/outputs.py
tpu_inference/interfaces/params.py
tpu_inference/interfaces/platform.py
tpu_inference/interfaces/request.py
tpu_inference/interfaces/scheduler.py
tpu_inference/kernels/__init__.py
tpu_inference/kernels/collectives/__init__.py
tpu_inference/kernels/collectives/all_gather_matmul.py
tpu_inference/kernels/collectives/all_gather_matmul_tuned_block_sizes.py
tpu_inference/kernels/collectives/util.py
tpu_inference/kernels/flash_attention/__init__.py
tpu_inference/kernels/flash_attention/kernel.py
tpu_inference/kernels/quantized_matmul/__init__.py
tpu_inference/kernels/quantized_matmul/kernel.py
tpu_inference/kernels/quantized_matmul/tuned_block_sizes.py
tpu_inference/kernels/quantized_matmul/util.py
tpu_inference/kernels/ragged_paged_attention/__init__.py
tpu_inference/kernels/ragged_paged_attention/v2/__init__.py
tpu_inference/kernels/ragged_paged_attention/v2/kernel.py
tpu_inference/kernels/ragged_paged_attention/v2/ragged_kv_cache_update.py
tpu_inference/kernels/ragged_paged_attention/v2/tuned_block_sizes.py
tpu_inference/kernels/ragged_paged_attention/v3/__init__.py
tpu_inference/kernels/ragged_paged_attention/v3/kernel.py
tpu_inference/kernels/ragged_paged_attention/v3/tuned_block_sizes.py
tpu_inference/kernels/ragged_paged_attention/v3/util.py
tpu_inference/layers/__init__.py
tpu_inference/layers/common/__init__.py
tpu_inference/layers/common/attention_metadata.py
tpu_inference/layers/jax/__init__.py
tpu_inference/layers/jax/attention_interface.py
tpu_inference/layers/jax/base.py
tpu_inference/layers/jax/binary_search.py
tpu_inference/layers/jax/constants.py
tpu_inference/layers/jax/layers.py
tpu_inference/layers/jax/misc.py
tpu_inference/layers/jax/rope.py
tpu_inference/layers/jax/rope_interface.py
tpu_inference/layers/jax/sharding.py
tpu_inference/layers/jax/transformer_block.py
tpu_inference/layers/jax/attention/__init__.py
tpu_inference/layers/jax/attention/attention.py
tpu_inference/layers/jax/attention/deepseek_v3_attention.py
tpu_inference/layers/jax/attention/llama4_attention.py
tpu_inference/layers/jax/moe/__init__.py
tpu_inference/layers/jax/moe/deepseek_v3_moe.py
tpu_inference/layers/jax/moe/moe.py
tpu_inference/layers/jax/sample/__init__.py
tpu_inference/layers/jax/sample/rejection_sampler.py
tpu_inference/layers/jax/sample/sampling.py
tpu_inference/layers/jax/sample/sampling_metadata.py
tpu_inference/layers/vllm/__init__.py
tpu_inference/layers/vllm/attention.py
tpu_inference/layers/vllm/fused_moe.py
tpu_inference/layers/vllm/linear_common.py
tpu_inference/layers/vllm/sharding.py
tpu_inference/layers/vllm/quantization/__init__.py
tpu_inference/layers/vllm/quantization/awq.py
tpu_inference/layers/vllm/quantization/common.py
tpu_inference/layers/vllm/quantization/unquantized.py
tpu_inference/layers/vllm/quantization/compressed_tensors/__init__.py
tpu_inference/layers/vllm/quantization/compressed_tensors/compressed_tensors.py
tpu_inference/layers/vllm/quantization/compressed_tensors/schemes/__init__.py
tpu_inference/layers/vllm/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py
tpu_inference/layers/vllm/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_int8.py
tpu_inference/lora/__init__.py
tpu_inference/lora/torch_lora_ops.py
tpu_inference/lora/torch_punica_tpu.py
tpu_inference/mock/__init__.py
tpu_inference/mock/vllm_config_utils.py
tpu_inference/mock/vllm_envs.py
tpu_inference/mock/vllm_logger.py
tpu_inference/mock/vllm_logging_utils.py
tpu_inference/models/__init__.py
tpu_inference/models/common/__init__.py
tpu_inference/models/common/model_loader.py
tpu_inference/models/jax/__init__.py
tpu_inference/models/jax/deepseek_v3.py
tpu_inference/models/jax/llama3.py
tpu_inference/models/jax/llama4.py
tpu_inference/models/jax/llama_eagle3.py
tpu_inference/models/jax/phi3.py
tpu_inference/models/jax/qwen2.py
tpu_inference/models/jax/qwen2_5_vl.py
tpu_inference/models/jax/qwen3.py
tpu_inference/models/jax/utils/__init__.py
tpu_inference/models/jax/utils/file_utils.py
tpu_inference/models/jax/utils/multi_modal_utils.py
tpu_inference/models/jax/utils/weight_utils.py
tpu_inference/models/jax/utils/quantization/__init__.py
tpu_inference/models/jax/utils/quantization/quantization_utils.py
tpu_inference/models/vllm/__init__.py
tpu_inference/models/vllm/vllm_model_wrapper.py
tpu_inference/models/vllm/vllm_model_wrapper_context.py
tpu_inference/platforms/__init__.py
tpu_inference/platforms/tpu_jax.py
tpu_inference/runner/__init__.py
tpu_inference/runner/block_table_jax.py
tpu_inference/runner/compilation_manager.py
tpu_inference/runner/input_batch_jax.py
tpu_inference/runner/kv_cache.py
tpu_inference/runner/kv_cache_manager.py
tpu_inference/runner/lora_utils.py
tpu_inference/runner/multimodal_manager.py
tpu_inference/runner/persistent_batch_manager.py
tpu_inference/runner/speculative_decoding_manager.py
tpu_inference/runner/structured_decoding_manager.py
tpu_inference/runner/tpu_jax_runner.py
tpu_inference/runner/utils.py
tpu_inference/spec_decode/__init__.py
tpu_inference/spec_decode/jax/__init__.py
tpu_inference/spec_decode/jax/eagle3.py
tpu_inference/worker/__init__.py
tpu_inference/worker/_temporary_vllm_compat.py
tpu_inference/worker/base.py
tpu_inference/worker/tpu_worker_jax.py