tpu-inference 0.11.1rc1__tar.gz → 0.11.1rc2__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.


This version of tpu-inference might be problematic. Click here for more details.

Files changed (131) hide show
  1. {tpu_inference-0.11.1rc1/tpu_inference.egg-info → tpu_inference-0.11.1rc2}/PKG-INFO +1 -1
  2. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2/tpu_inference.egg-info}/PKG-INFO +1 -1
  3. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/LICENSE +0 -0
  4. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/MANIFEST.in +0 -0
  5. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/README.md +0 -0
  6. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/pyproject.toml +0 -0
  7. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/requirements.txt +0 -0
  8. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/setup.cfg +0 -0
  9. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/setup.py +0 -0
  10. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tests/__init__.py +0 -0
  11. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tests/core/__init__.py +0 -0
  12. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tests/core/test_adapters.py +0 -0
  13. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tests/core/test_core_tpu.py +0 -0
  14. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tests/core/test_disagg_executor.py +0 -0
  15. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tests/core/test_disagg_utils.py +0 -0
  16. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tests/core/test_init.py +0 -0
  17. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tests/kernels/__init__.py +0 -0
  18. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tests/kernels/quantized_matmul_kernel_test.py +0 -0
  19. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tests/kernels/ragged_kv_cache_update_v2_test.py +0 -0
  20. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tests/kernels/ragged_paged_attention_kernel_v2_test.py +0 -0
  21. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tests/kernels/ragged_paged_attention_kernel_v3_test.py +0 -0
  22. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tests/lora/__init__.py +0 -0
  23. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tests/lora/test_lora.py +0 -0
  24. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tests/test_base.py +0 -0
  25. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tests/test_quantization.py +0 -0
  26. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tests/test_tpu_info.py +0 -0
  27. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tests/test_utils.py +0 -0
  28. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tests/tpu_backend_test.py +0 -0
  29. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/__init__.py +0 -0
  30. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/adapters/__init__.py +0 -0
  31. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/adapters/vllm_adapters.py +0 -0
  32. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/adapters/vllm_config_adapters.py +0 -0
  33. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/backend.py +0 -0
  34. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/core/__init__.py +0 -0
  35. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/core/adapters.py +0 -0
  36. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/core/core_tpu.py +0 -0
  37. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/core/disagg_executor.py +0 -0
  38. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/core/disagg_utils.py +0 -0
  39. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/di/__init__.py +0 -0
  40. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/di/abstracts.py +0 -0
  41. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/di/host.py +0 -0
  42. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/di/interfaces.py +0 -0
  43. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/distributed/__init__.py +0 -0
  44. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/distributed/tpu_connector.py +0 -0
  45. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/distributed/utils.py +0 -0
  46. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/executors/__init__.py +0 -0
  47. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/executors/ray_distributed_executor.py +0 -0
  48. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/experimental/__init__.py +0 -0
  49. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/experimental/llama3_jax_stashed.py +0 -0
  50. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/interfaces/__init__.py +0 -0
  51. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/interfaces/cache.py +0 -0
  52. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/interfaces/config.py +0 -0
  53. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/interfaces/config_parts.py +0 -0
  54. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/interfaces/engine.py +0 -0
  55. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/interfaces/outputs.py +0 -0
  56. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/interfaces/params.py +0 -0
  57. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/interfaces/platform.py +0 -0
  58. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/interfaces/request.py +0 -0
  59. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/interfaces/scheduler.py +0 -0
  60. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/kernels/__init__.py +0 -0
  61. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/kernels/flash_attention/__init__.py +0 -0
  62. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/kernels/flash_attention/kernel.py +0 -0
  63. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/kernels/quantized_matmul/__init__.py +0 -0
  64. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/kernels/quantized_matmul/kernel.py +0 -0
  65. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/kernels/quantized_matmul/tuned_block_sizes.py +0 -0
  66. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/kernels/quantized_matmul/util.py +0 -0
  67. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/kernels/ragged_paged_attention/__init__.py +0 -0
  68. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/kernels/ragged_paged_attention/v2/__init__.py +0 -0
  69. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/kernels/ragged_paged_attention/v2/kernel.py +0 -0
  70. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/kernels/ragged_paged_attention/v2/ragged_kv_cache_update.py +0 -0
  71. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/kernels/ragged_paged_attention/v2/tuned_block_sizes.py +0 -0
  72. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/kernels/ragged_paged_attention/v3/__init__.py +0 -0
  73. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/kernels/ragged_paged_attention/v3/kernel.py +0 -0
  74. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/kernels/ragged_paged_attention/v3/tuned_block_sizes.py +0 -0
  75. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/kernels/ragged_paged_attention/v3/util.py +0 -0
  76. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/logger.py +0 -0
  77. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/lora/__init__.py +0 -0
  78. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/lora/torch_lora_ops.py +0 -0
  79. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/lora/torch_punica_tpu.py +0 -0
  80. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/mock/__init__.py +0 -0
  81. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/mock/vllm_config_utils.py +0 -0
  82. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/mock/vllm_envs.py +0 -0
  83. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/mock/vllm_logger.py +0 -0
  84. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/mock/vllm_logging_utils.py +0 -0
  85. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/models/__init__.py +0 -0
  86. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/models/jax/__init__.py +0 -0
  87. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/models/jax/deepseek_v3.py +0 -0
  88. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/models/jax/llama3.py +0 -0
  89. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/models/jax/llama4.py +0 -0
  90. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/models/jax/llama_eagle3.py +0 -0
  91. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/models/jax/phi3.py +0 -0
  92. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/models/jax/qwen2.py +0 -0
  93. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/models/jax/qwen2_5_vl.py +0 -0
  94. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/models/jax/qwen3.py +0 -0
  95. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/models/jax/utils/__init__.py +0 -0
  96. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/models/jax/utils/file_utils.py +0 -0
  97. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/models/jax/utils/multi_modal_utils.py +0 -0
  98. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/models/jax/utils/quantization/__init__.py +0 -0
  99. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/models/jax/utils/quantization/quantization_utils.py +0 -0
  100. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/models/jax/utils/weight_utils.py +0 -0
  101. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/models/vllm/__init__.py +0 -0
  102. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/models/vllm/vllm_model_wrapper.py +0 -0
  103. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/models/vllm/vllm_model_wrapper_context.py +0 -0
  104. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/platforms/__init__.py +0 -0
  105. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/platforms/tpu_jax.py +0 -0
  106. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/runner/__init__.py +0 -0
  107. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/runner/block_table_jax.py +0 -0
  108. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/runner/compilation_manager.py +0 -0
  109. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/runner/input_batch_jax.py +0 -0
  110. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/runner/kv_cache.py +0 -0
  111. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/runner/kv_cache_manager.py +0 -0
  112. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/runner/lora_utils.py +0 -0
  113. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/runner/multimodal_manager.py +0 -0
  114. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/runner/persistent_batch_manager.py +0 -0
  115. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/runner/speculative_decoding_manager.py +0 -0
  116. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/runner/structured_decoding_manager.py +0 -0
  117. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/runner/tpu_jax_runner.py +0 -0
  118. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/runner/utils.py +0 -0
  119. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/spec_decode/__init__.py +0 -0
  120. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/spec_decode/jax/__init__.py +0 -0
  121. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/spec_decode/jax/eagle3.py +0 -0
  122. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/tpu_info.py +0 -0
  123. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/utils.py +0 -0
  124. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/worker/__init__.py +0 -0
  125. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/worker/_temporary_vllm_compat.py +0 -0
  126. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/worker/base.py +0 -0
  127. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference/worker/tpu_worker_jax.py +0 -0
  128. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference.egg-info/SOURCES.txt +0 -0
  129. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference.egg-info/dependency_links.txt +0 -0
  130. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference.egg-info/requires.txt +0 -0
  131. {tpu_inference-0.11.1rc1 → tpu_inference-0.11.1rc2}/tpu_inference.egg-info/top_level.txt +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: tpu_inference
3
- Version: 0.11.1rc1
3
+ Version: 0.11.1rc2
4
4
  Author: tpu_inference Contributors
5
5
  Classifier: Development Status :: 3 - Alpha
6
6
  Classifier: Intended Audience :: Developers
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: tpu_inference
3
- Version: 0.11.1rc1
3
+ Version: 0.11.1rc2
4
4
  Author: tpu_inference Contributors
5
5
  Classifier: Development Status :: 3 - Alpha
6
6
  Classifier: Intended Audience :: Developers