tpu-inference 0.11.1.dev202511270815__py3-none-any.whl → 0.13.0rc2.post7__py3-none-any.whl

tpu_inference-0.13.0rc2.post7.dist-info/RECORD

@@ -0,0 +1,261 @@
+tests/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tests/test_base.py,sha256=47IflI4nIktZHlcmeqhmX9IdTKofg7OgsOiCyUTXlLw,7916
+tests/test_envs.py,sha256=v0_R-HfWRNY8ssPqFrytHMl1irohJaTpS_rSKo2FZaY,10021
+tests/test_tpu_info.py,sha256=OrA0Fbs9uCVqd8w7dqlGA_8KZArriyltqrCWf3hDDDU,5245
+tests/test_utils.py,sha256=FF_41NL1VmUXDVvKr9eZg_juprqtHlUqSPR6Sisftdo,6309
+tests/core/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tests/core/test_core_tpu.py,sha256=r496rk1eOsK_F4nvm9zprl_T-RcO6eCUb7LuVReOZno,21413
+tests/core/test_disagg_executor.py,sha256=QdE2YZs08EyDDCmSjhiXkXqQ9BJTgO6csr_E1xkkfSg,2256
+tests/core/test_disagg_utils.py,sha256=A5icdqkJlau2PHYAxHfHKuqrlEKXVJu2nm02XOrXjcc,2530
+tests/core/test_dp_scheduler.py,sha256=m6ph_OH9tXz6AxNde8cIjptd1lwDVSCqIV2Ef-cNJFk,34253
+tests/core/test_init.py,sha256=5BDDC-dmDtWEGaBPjQSiYJuMiwTBVRSDx9p7Cv8DKyI,2262
+tests/distributed/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tests/distributed/test_distributed_utils.py,sha256=YXKbSG9J72vCrU5mPiFf1ya-Yzc1BjeahdBmQVez8Wc,5031
+tests/distributed/test_tpu_connector.py,sha256=ajKeRUi3x29hQXfLrSlo6yDczpwZsg_mGt2vKBGRZdk,20538
+tests/e2e/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tests/e2e/test_async_scheduler.py,sha256=215xGuyTEBSOe-c1l48TIjrCqhbVFZY3m5p3q5mU7jA,6905
+tests/e2e/test_data_parallel.py,sha256=KB-_BKic_iZyn4WbPWsUdVClinzd8g7PrQ0ui5B-nwo,10725
+tests/e2e/test_hybrid_kvcache.py,sha256=Y7a-grjvAKBbp7vbQncVEQKGM1WxcwO0qa2o0opKiEI,8076
+tests/e2e/test_local_disagg.py,sha256=xIjYI6RGA6bZk4dluklhfYBoJGbHkrSihSkJtPgpZv4,10434
+tests/e2e/test_model_loader.py,sha256=DYlS420KXkNzeIijAf-0UQsYH0pOAGcXRl6P99PBiAc,9366
+tests/e2e/test_multi_modal_inference.py,sha256=hVatj8Rra6XAekp6zBxRivQUcGiV8SimPph9cZ-TJyk,3896
+tests/e2e/test_pipeline_parallel.py,sha256=VpxY9wgQj3-i0XooHZHdmHGdMS3ilmHbxu6ZfyQDUP0,9519
+tests/e2e/test_runai_model_streamer_loader.py,sha256=MXUxKfKV7vVM_LI7-5hBV-wCswogPENkMPsREUjFu3I,3790
+tests/e2e/test_sampling_params.py,sha256=ibLWtJfS35HughdOBtXD2IcyWPXoZA4R4KwXz-RzgOY,10683
+tests/e2e/test_speculative_decoding.py,sha256=tj3VSJEi7r9aHjywZanlmfY4eS5Tfr5zPe9TH3PW5EY,9911
+tests/e2e/test_structured_decoding.py,sha256=QYh9WjGrzm7syeLrGUawA6cOkWlQqVpTn7W6qwt65NY,1863
+tests/executors/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tests/executors/test_ray_distributed_executor.py,sha256=rMazBfirGsehEUXgpIPJkw0z7xO4cnK2kzcgxjFA6Bo,8435
+tests/experimental/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tests/experimental/test_llama3_jax_stashed.py,sha256=Ruypll_7QQOdjPmF0vDL_JVk41AHnULWuJtlgscSuZQ,8126
+tests/kernels/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tests/kernels/fused_moe_v1_test.py,sha256=cnMuvS_PD29F6whBioZlikWFrDXOMHwVPdSu2x-OJR0,10978
+tests/kernels/gmm_test.py,sha256=rWE5fnp6hAV1FaGHjHjfScfIcoHuQ5wMdRGzhjt6Qnc,6820
+tests/kernels/mla_v1_test.py,sha256=Rmhk8jHWeXwZmouza0o_z4NqAaac5mEo9lN1ychln9I,16076
+tests/kernels/quantized_matmul_kernel_test.py,sha256=9Q3ufAG6NY9jeEFcre_IY2JbwpQdYzzhMWbXb5yfY6Q,4796
+tests/kernels/ragged_kv_cache_update_v2_test.py,sha256=A12DnEqB0WtAWsD6ruF49RC4zrFcFM7CrGomElxE7jU,11396
+tests/kernels/ragged_paged_attention_kernel_v2_test.py,sha256=1SSg9EzlLIdIQQw3BMoaEWbHVp30XY2A3FQS85ot4ss,11915
+tests/kernels/ragged_paged_attention_kernel_v3_hd64_test.py,sha256=Ugs1DBBC-ZUuhQBomqGIqUKNiawqD539Rr1BqyNaqUQ,17007
+tests/kernels/ragged_paged_attention_kernel_v3_test.py,sha256=HS60dynUGT096wCkkau4W3KJQyEQyB06P4j0LLd9-RA,15524
+tests/kernels/collectives/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tests/kernels/collectives/all_gather_matmul_kernel_test.py,sha256=ftp3CMoqiZdzD8vH0P9vNaiJx7FUICKUyxLduTqcsTk,2383
+tests/layers/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tests/layers/common/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tests/layers/common/test_attention_interface.py,sha256=ke6h-e8CP-FhNY_ojKCYwyHgYG8aSvik1cEjCGH3VRk,5063
+tests/layers/common/test_quantization.py,sha256=JcwDrNTm6UlBSV3s3mwwvpxOjqBpZDJwnYYoj3DnS7A,5344
+tests/layers/jax/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tests/layers/jax/test_layers.py,sha256=L1xh_wniBtlfudya_WRmHUWOhEno0i6ikKE1XiBtaZs,5010
+tests/layers/jax/test_qwix.py,sha256=G7PrmkWkhQD8P0RvwnF-iyRoXO4d7g1Ce4ycaIjDQ_0,39727
+tests/layers/jax/test_rope.py,sha256=0biwYRSRsKMaRHknc8v8Tfrt0bmJKQGeQLPqR_D04mM,3565
+tests/layers/jax/test_sharding.py,sha256=Hk1MWhIluOKIBx7-O9fKa1n6fF3SW7UMYsRI9AGzp_0,5914
+tests/layers/jax/test_transformer_block.py,sha256=Wpgowc0ZJnv1GUxcK-Op6CCYWjpqgUM0p3EANk-YWzc,5742
+tests/layers/jax/attention/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tests/layers/jax/attention/test_common_attention.py,sha256=gXixLH2HosBp86PVwhRvwrTVVj4tl54VjrOCovwmmqM,3845
+tests/layers/jax/attention/test_deepseek_v3_attention.py,sha256=hKxrUu4E8yfhIPj5V29p16xQxOXDvEQDzBZpyiAya3o,9292
+tests/layers/jax/attention/test_llama4_attention.py,sha256=t1Kj0oTSFj_cVNuLl-ceZ-BY91sjx04xNRg_Epxjank,4980
+tests/layers/jax/moe/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tests/layers/jax/moe/test_deepseek_moe.py,sha256=2v7o2Svz1z6LH9tNqbL7dZtu5PSuKGiJzUccE-AMUYc,10550
+tests/layers/jax/sample/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tests/layers/jax/sample/test_rejection_sampler.py,sha256=qHvFpm-Oo6ZO0KHBN6nCB00BinbpCqxlg_QsSkAX-cI,65362
+tests/layers/jax/sample/test_sampling.py,sha256=oCgI2YBnz5NCdwr2CWsiEFkddXnke1_S1tAIFP7D1oc,4098
+tests/layers/jax/sample/test_sampling_metadata.py,sha256=WQCmgGkkn7sgBL9Uq7REdAkTUXq9YhbhBeuMTFtSIe8,9198
+tests/layers/vllm/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tests/layers/vllm/test_attention.py,sha256=NSbeKIi4eQj9RLiHeT-aEDvvsiHYbD3rk4uXq3_5_X8,13193
+tests/layers/vllm/test_awq.py,sha256=0aFURqn3zh0Ueytvfzy6SGon0gPRzk8Dn0DuCnpu_XQ,14479
+tests/layers/vllm/test_compressed_tensors_moe.py,sha256=jlMZcbQWlgaLX4pAlEMjZbJ7a0NyjxIhqXUW5DGH6KM,7385
+tests/layers/vllm/test_compressed_tensors_w8a8_fp8.py,sha256=eTXSWaPcKgOEAyWt7Xqqkhd0fa2J3QFa3QJBRQjTsaY,15521
+tests/layers/vllm/test_compressed_tensors_w8a8_int8.py,sha256=dCKHPos33MIwJnK96zlIUvJYN0PpRPXdyPyo-PnKH3U,16555
+tests/layers/vllm/test_fp8.py,sha256=ZvFTg4Umgg6W2RwElkIZ_Rls_XZJ8sEW7yww2K3ztf4,666
+tests/layers/vllm/test_mxfp4.py,sha256=sFer788F7pbDUtB0yB6WU9Lh9kzUOaxXP6XXVsvQHrc,11625
+tests/layers/vllm/test_unquantized.py,sha256=iqoqib_Rv2DdmKA2ub6T6cIT67PSTc3s7gpYzBTs_qI,24432
+tests/layers/vllm/utils.py,sha256=Qk67IqSrSovhPlWmDGFBr5vwgwtG7kcUzy69-oPgR0A,3105
+tests/lora/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tests/lora/conftest.py,sha256=OI4gPV4vNOCcfE93ccmIWQHd8-Gp9c2yGVlaSnuT4Tg,1559
+tests/lora/test_bgmv.py,sha256=B1HCjh27379vCxZsd8nKMBZ8lr1JamuuWDgYiALyn18,1934
+tests/lora/test_layers.py,sha256=K4Vnu19BKJw82qL9Si76lavdShOPsY5YqCHbMw09Fto,26553
+tests/lora/test_lora.py,sha256=Wqc6V7wQkobP-F8kHUkuMuiQYnxN775xlLUjDz6cEp0,5012
+tests/lora/test_lora_perf.py,sha256=zcZud9Hexx6wa9qX0IvnjKyDD-i61NdIQrVO31Yx3vU,2381
+tests/lora/utils.py,sha256=rY0tDZEZe58ye4-ykwrTnsiWuLcaEG57N_Rua90bDXI,2726
+tests/models/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tests/models/common/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tests/models/common/test_model_loader.py,sha256=Sf-k_Kxdjkz-lS_0-ICfA4Yk2VXX33esP8PNG4B7FzA,17392
+tests/models/jax/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tests/models/jax/test_deepseek_v3.py,sha256=9RY6ypfvPts3NOnvWu9n_T7pUjrvj_QY_saLOKpFg4c,16243
+tests/models/jax/test_llama3.py,sha256=NYsT35yh9GzkYYcLcOo1BkBGGr14E89GtdCJJ6SFhI8,6610
+tests/models/jax/test_llama4.py,sha256=MMQzTymnVUdWZ6XoOD8k9Q2ikmAk6tFSGB1C5DCi7pw,12605
+tests/models/jax/test_llama_eagle3.py,sha256=DCk1ae9SLJUrqyx7uvNOmpqAAM09xb0rYNOst-Leo_M,7777
+tests/models/jax/test_llama_guard_4.py,sha256=w-8cKwuTRFyzDh2mxvAofrt5xUprZyqRm5DRVRamGwE,9322
+tests/models/jax/test_qwen2.py,sha256=xylG-LmHBSy76V-Yl5KiAXogpZPM2w3Mx0E61Ud5sO4,6227
+tests/models/jax/test_qwen2_5_vl.py,sha256=PfB_gecAvXNrksxt8E56yP6d8ioZZWMoUIvh-OrbzJ4,26299
+tests/models/jax/test_qwen3.py,sha256=NWLAZPwGIhZjW0OADk4JqU4ZPn8JGSGPwkbTQvKEc50,6021
+tests/models/jax/test_weight_loading.py,sha256=RlmByQcjrsefybeNlS9wnL522be6CSR7YLcb7O5eZ-A,5205
+tests/models/jax/utils/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tests/models/jax/utils/test_multi_modal_utils.py,sha256=xrD8GijHGzb-n6z1W0okdjdNfREC1A9ZU7FQcbrx8zM,7867
+tests/platforms/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tests/platforms/test_tpu_platform.py,sha256=L0WUMncWzlWYWPAbtrE6Lhj-BuSjq-Ml2iKIjlmFGFE,2149
+tests/runner/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tests/runner/test_block_table.py,sha256=gFGF425mpWfOLjnQeQiG18TqFko8vpilJ3AiiiV1j8Y,14732
+tests/runner/test_input_batch.py,sha256=7nEkB00JrhaKCKf1ep28iedYbNbuqEdaQAxYqHaXThc,8198
+tests/runner/test_kv_cache.py,sha256=TvxmJNI8lM0ZNllZonHySA8NCQZ7prBgNODpYEI787E,7394
+tests/runner/test_kv_cache_manager.py,sha256=dYVWQamfGwqytnumfvjRt2r3n9BRBqcSbCXGWnw1SXs,22461
+tests/runner/test_multimodal_manager.py,sha256=8RbHHMvRuHg1Scc0b70tsr-tF2lfk8SZVx3InVgIryc,18591
+tests/runner/test_persistent_batch_manager.py,sha256=EW6P-BtI4i59Clx-Lh84fU1GtDKF3Av2gtO-rCRYN_k,3148
+tests/runner/test_speculative_decoding_manager.py,sha256=HgemtiBL_VhBheUgem3OpPj6yBK9vdJsL8VCABQdGXw,16093
+tests/runner/test_structured_decoding_manager.py,sha256=pVX3z2TLR6SfBoEyRtv0BPajHbMVdcOAe4opMoxEpps,9802
+tests/runner/test_tpu_runner.py,sha256=H1RjGGvNPfNNhglbiUs9J2QsokXaDtnmmtdoYRvA5_8,11649
+tests/runner/test_tpu_runner_dp.py,sha256=TAEmI-JaIodgYNjjjQAAQg-q0bSbeVON5ZZE2jngfOk,50851
+tests/runner/test_tpu_runner_mesh.py,sha256=kDyjdnd0vO4GQrcOAPLr9TEYA49-qDFE4gHt9IL6wlk,8638
+tests/runner/test_utils.py,sha256=_R2bnKttqgg7vfPXP0Qfx38mr-4UBm2UMIbuQFAwgWk,15442
+tests/spec_decode/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tests/spec_decode/test_eagle3.py,sha256=18GbBKaMipCekyZMn24Fp-lraGEiASj2t-blohqWu7Y,12945
+tests/worker/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tests/worker/tpu_worker_test.py,sha256=lfRMW_DG2f9juR0I60uW682iDa9QvLNdtU-VLfJPUdY,17520
+tpu_inference/__init__.py,sha256=2LJVEi6eR-RWHifo68n6D0SKYgg1NLrruW_E7Lz3oxg,2879
+tpu_inference/env_override.py,sha256=pmL7lfs_rGCP92ya3wuWuudsCYeOMZ6tFZY82A4KkQc,365
+tpu_inference/envs.py,sha256=A1Bdm5qiXhTdu-Q_yNzBpi79_nOJIDbdFF7MAMqmjxo,6662
+tpu_inference/logger.py,sha256=HQCz7NefmbturuhOC7-3Ixbtcdgoz4g9FHh2RB6o8cc,334
+tpu_inference/tpu_info.py,sha256=lty-ngN1uUvQLlFGkWa2u5eEb5anwmcv_uyI0S95PdY,2840
+tpu_inference/utils.py,sha256=0fQXcZJ4IiPGlNv_bLdkla5FeEEKEzyTsSDH-y47ouo,10641
+tpu_inference/core/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/core/core_tpu.py,sha256=WDD3koE_j1QhWS2BbMA2aQOZayPZm4tYPvzL4YCX2jY,33294
+tpu_inference/core/disagg_executor.py,sha256=HZpgYMVxRxm0RQxO4l8IDYBWJ6Z3Tac6xavc5otcirc,4657
+tpu_inference/core/disagg_utils.py,sha256=lv8MAVoAjtcmTaenUXVokg2q3d0tzsma86UiQlQ3omY,1492
+tpu_inference/core/sched/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/core/sched/dp_scheduler.py,sha256=-7d2zopJ5ZJFIJ8LbHsm_4bBBtP7qrim4XWVPDF6vrg,34960
+tpu_inference/distributed/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/distributed/jax_parallel_state.py,sha256=xMK0tEtblh37_LoHvp1-6qPI8AgX4HkE0ATuc7fdHKs,2798
+tpu_inference/distributed/tpu_connector.py,sha256=3rR0y2P1MOOSM8nBfvl95ZQcVKMms3rL8zTdnxUmSms,29946
+tpu_inference/distributed/utils.py,sha256=8pTkqI81b7Gkurn6M4zepoTUmTRaab3kfrH4ncAf5ns,3738
+tpu_inference/executors/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/executors/ray_distributed_executor.py,sha256=5dP1wPk_YRzqXJBXqWDnz3BXauyBMSBMWn7uGdLK8HY,16968
+tpu_inference/experimental/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/experimental/llama3_jax_stashed.py,sha256=39XTuG-0C5pZe1oDznm6iCrvccZ_2CnC488YsvhxIho,11488
+tpu_inference/kernels/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/kernels/collectives/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/kernels/collectives/all_gather_matmul.py,sha256=TtQWY0lNj8699JwDmjqbRrdku-3oAw5WkuuoFPS49AY,27597
+tpu_inference/kernels/collectives/all_gather_matmul_tuned_block_sizes.py,sha256=OEPf4q08IeIFyJfzizgRs6kSD7w35NeZDRIn7CcZ344,1468
+tpu_inference/kernels/collectives/util.py,sha256=LbLD6lOxuszbUsykF89gWQqEJUICCZsfzam3EJDPnFE,1859
+tpu_inference/kernels/flash_attention/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/kernels/flash_attention/kernel.py,sha256=n8gmAFVfchMXlyaSEj8xXJm6AadFt26edQihPRdithY,25897
+tpu_inference/kernels/fused_moe/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/kernels/fused_moe/v1/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/kernels/fused_moe/v1/kernel.py,sha256=B0qWaa5vphIa3MJmeTbvpBMh9JJlRWNpmoORrz79Cvk,64990
+tpu_inference/kernels/megablox/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/kernels/megablox/common.py,sha256=CoJPNom6anJU9B4i05d2skytJEvNS994DYo0eEyVGuY,1639
+tpu_inference/kernels/megablox/gmm.py,sha256=rVW70SGPshR9XvHiwzmskX4_yeD4nE8or3RfabwcCLM,24240
+tpu_inference/kernels/mla/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/kernels/mla/v1/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/kernels/mla/v1/kernel.py,sha256=oovjb0x3qz08IL_KVjLLbNbcEcFXip55fqgIgfnl3RA,49758
+tpu_inference/kernels/quantized_matmul/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/kernels/quantized_matmul/kernel.py,sha256=-A9Kd2ApHWgPvCaUPfjM5JooLz_iCfWV1UT0taaZaAo,16264
+tpu_inference/kernels/quantized_matmul/tuned_block_sizes.py,sha256=3zhIm73JEE8qOty2_0v3AJlVz13k6qMB5wlXBDyC1EM,35130
+tpu_inference/kernels/quantized_matmul/util.py,sha256=rf6nIiAj9I2cj4LDvtaZGhcLXEc94o2xgMWasnFaREM,1943
+tpu_inference/kernels/ragged_paged_attention/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/kernels/ragged_paged_attention/v2/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/kernels/ragged_paged_attention/v2/kernel.py,sha256=462jgsWdnaQfO9K1Y99cJ-qidYWXZMc5GdoY9enQEWY,35019
+tpu_inference/kernels/ragged_paged_attention/v2/ragged_kv_cache_update.py,sha256=y9-C_F28WGd282Ra_DqwTbHyUIIj2jyWY3DiX8yozHY,11080
+tpu_inference/kernels/ragged_paged_attention/v2/tuned_block_sizes.py,sha256=mw80bXBGenroGdrITV0F_EaI2s-Z9KWwqU9WodvJg14,97919
+tpu_inference/kernels/ragged_paged_attention/v3/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/kernels/ragged_paged_attention/v3/kernel.py,sha256=HVTQ4LJiEkWiYuUV1ey-2K2u6IULjJQ2dbX3qpo3FLA,60593
+tpu_inference/kernels/ragged_paged_attention/v3/kernel_hd64.py,sha256=VutC0CwPfF-luuRSPv6b7QiFt2EBiCPdoTMtOrFFZtI,60391
+tpu_inference/kernels/ragged_paged_attention/v3/tuned_block_sizes.py,sha256=sG67fBe8ckXdfvO7c9gfGFhu6_8owir8ZE6IOyHhNFY,231477
+tpu_inference/kernels/ragged_paged_attention/v3/tuned_block_sizes_hd64.py,sha256=WusgnI6oDRsUoF8lp4vsaPepKO8oTJLlPSlLDpr3-7Y,25025
+tpu_inference/kernels/ragged_paged_attention/v3/util.py,sha256=VVYHEHmANvEddEKx8IPTRSXDykwzEOJa2GZKNv7nwnM,1755
+tpu_inference/layers/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/layers/common/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/layers/common/attention_interface.py,sha256=WNEXNj1_6mDNS4KDXJRu9hkbJmKFlsp78txbqbDWhTo,13712
+tpu_inference/layers/common/attention_metadata.py,sha256=rmipY517sefHe4owxC5USkm4lbL4zd4LZKokDYGECQo,1425
+tpu_inference/layers/common/binary_search.py,sha256=ZQi-z1wG6WTcfVQXeTGOZokX4K1DSf9kCzqfrhEU8lk,12320
+tpu_inference/layers/common/quant_methods.py,sha256=SCm9g7bE02XSMONmOCuT0vfHeTP6RzGQ57aTj919HgM,772
+tpu_inference/layers/common/quantization.py,sha256=cTuoCpU3qBdPvoy_6R6uwCyz9ojh6esvl9x3bQeMbs4,8710
+tpu_inference/layers/common/sharding.py,sha256=curCejZPj8ND4rxjWEbwRozkFYlK_HlpIyTywhDHcWU,26171
+tpu_inference/layers/jax/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/layers/jax/base.py,sha256=UhT4ut_59ynUPdaZGpMPSCQkPTWXA9BxkaPy7lDhoLI,6350
+tpu_inference/layers/jax/constants.py,sha256=YQJOeAbja1yTbPhoOWMp24OF1RCMwPybK1NIwPrrYJ0,3329
+tpu_inference/layers/jax/layers.py,sha256=elv04eCMFj5Jt3SF0PXxyuQPTwmJDgsuvZ9oK88HTso,11208
+tpu_inference/layers/jax/misc.py,sha256=Jdxv8SAT1yVuM_1_lGWImRSXlu2xGLnXI-TRGRNsBYw,1141
+tpu_inference/layers/jax/pp_utils.py,sha256=gP3Xt-Pinm6E7yJ9jtsSnmmoz9GmgBN83TkSgIrz0OA,1726
+tpu_inference/layers/jax/rope.py,sha256=FbZKJPd9T0IDaZyOJkrFl2CL1on1womCzZBiUPLU0O4,11924
+tpu_inference/layers/jax/rope_interface.py,sha256=cPqVpKG5_SU7S7xcrMEaPBJLqi1nC4uMN-1S-dmb0mQ,8950
+tpu_inference/layers/jax/transformer_block.py,sha256=HTI0fYPQd23UbnJSB_pL2K3un3q_i3guvJiNCUReVRs,4492
+tpu_inference/layers/jax/attention/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/layers/jax/attention/attention.py,sha256=_N5W4ox8EzC1CZYcIhsEi35X8WCIMFEBlSzVtDDcTu8,10623
+tpu_inference/layers/jax/attention/deepseek_v3_attention.py,sha256=KP-hgck-wTzTcwDNB08DwNiqsE-6OD4tQ1jLVwWQvEw,22427
+tpu_inference/layers/jax/attention/gpt_oss_attention.py,sha256=EM1kJpr77VHh95aSD5UnSJazB_anS_7PyaD8TixVMrY,9241
+tpu_inference/layers/jax/attention/llama4_attention.py,sha256=QzBDoEioI9mMdI1T2LNlsr89iaGl234e-9s202YWS8M,6713
+tpu_inference/layers/jax/moe/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/layers/jax/moe/deepseek_v3_moe.py,sha256=5j6TJO8fAB2Yv6mVAeM2F9WLe4QDM9bf6zxtdKjHjCQ,26456
+tpu_inference/layers/jax/moe/gpt_oss_moe.py,sha256=-uliFqHJFOTT9WJCEpGhkImOXMSoo3aePXMOmKXlgmk,6771
+tpu_inference/layers/jax/moe/moe.py,sha256=E7L8bJucTVke89o048GAbWdtuQIL5oDz-MkW0NK4E00,10114
+tpu_inference/layers/jax/sample/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/layers/jax/sample/rejection_sampler.py,sha256=VqN0mxi7Xg58w4EXS625ndC8NyA_UZMV9bjFM1mkvrY,21000
+tpu_inference/layers/jax/sample/sampling.py,sha256=IfJBFSXuTdd0QELn8Opmh7HgdzKreIwGYUOskTFp4aI,3888
+tpu_inference/layers/jax/sample/sampling_metadata.py,sha256=bip7TQcw-VHyN6072zBQY-tA0-QTyJpnuYg04mw9Sv0,3136
+tpu_inference/layers/vllm/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/layers/vllm/attention.py,sha256=LMQbS2KAup0Q-mmN5pzV6uUs-qdGpTSH8eV6ByHde9g,7370
+tpu_inference/layers/vllm/fused_moe.py,sha256=NdMVpDLI5-5274EuhVtH8KZzCnLBqSZSSvRoZqzwY7s,19868
+tpu_inference/layers/vllm/linear_common.py,sha256=--jpy8vf0RkZ0jDU1QfXT-V-RnjIloNSodYQKiw4Txo,9129
+tpu_inference/layers/vllm/sharding.py,sha256=f3pu7CJNRkfq5j1bmhmTM5wU9HwAePH3yWeTmaIINAw,9926
+tpu_inference/layers/vllm/quantization/__init__.py,sha256=XYe1VwgoFqLTuLJ-i-64hzNNMSWOkoErLTA_4N_Cze0,2463
+tpu_inference/layers/vllm/quantization/awq.py,sha256=nlWwR08lPlE_HIXLoDiGS2pOAJEiI0ukUGXos0NpbAE,9072
+tpu_inference/layers/vllm/quantization/common.py,sha256=GXYEvnhvRF8VWX0SHkzRpV3_LoQgAwCmXwLbEEwSm8A,5021
+tpu_inference/layers/vllm/quantization/fp8.py,sha256=_NT7QOD-N3UAJnYSDJD24Tsp8FaSK6NuDYp78QOTyzo,4530
+tpu_inference/layers/vllm/quantization/mxfp4.py,sha256=oS7e40ovqmipDKiHfpezzdP2RaFSNeXw6zv2nTrwKvc,18214
+tpu_inference/layers/vllm/quantization/unquantized.py,sha256=LPGRKw3lkeCHCJsY70P_hDUagnmI5bNe1cHuTFUEBkc,16701
+tpu_inference/layers/vllm/quantization/compressed_tensors/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/layers/vllm/quantization/compressed_tensors/compressed_tensors.py,sha256=2RS8owCqKHXZbtWKNjdKtsfzKH9N60UyqD-ug1A83oE,5914
+tpu_inference/layers/vllm/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=aOme0LFnhVeXDxdSw-Z0k5MZutM3-EoF2vwffezCARE,11277
+tpu_inference/layers/vllm/quantization/compressed_tensors/schemes/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/layers/vllm/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py,sha256=NkYl1K0RAd_gsOSjljLwmIr3kACC2EzhE_UsuqHhMiU,9334
+tpu_inference/layers/vllm/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_int8.py,sha256=-O8yQDuk-ZqzI0A2krobeCHxMc26nfuKBwUfzKi13xM,5777
+tpu_inference/lora/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/lora/torch_lora_ops.py,sha256=YR3Hj8nLLiQ-6wXy4uFsjQxFTbJYZ4o5dh_L0mlXg-o,3261
+tpu_inference/lora/torch_punica_tpu.py,sha256=qTnXZGLoOgvukSxeunO_SfpPTlkq9GlMj9H7zVYg9LE,12680
+tpu_inference/models/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/models/common/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/models/common/model_loader.py,sha256=TnTTION_J3nMGsIMJFuMzoBSl3VHHvhretmF5gMkyXI,21679
+tpu_inference/models/jax/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/models/jax/deepseek_v3.py,sha256=mje3RgxE1NwKWVLgJnPq3ebWB1J8T6YGHT2TtxN10Dg,45031
+tpu_inference/models/jax/gpt_oss.py,sha256=bgdsCx3UcTqEJatWBYbma5HNHH8GEaHN4aL5IsAeSmM,21592
+tpu_inference/models/jax/jax_intermediate_tensor.py,sha256=XKpDgPkOiRtYaPrW76ILxcp2uFfSiE1JMdqHWGo0-Ss,3179
+tpu_inference/models/jax/llama3.py,sha256=FjTGC69V_EJmvb5BIqYu3V5NS1Pvy-5Pb34kMn5YU5U,16317
+tpu_inference/models/jax/llama4.py,sha256=Ssycb5fcGjhJYg8FfcNckVhow7bvVt0FJbbpHinzMAA,30206
+tpu_inference/models/jax/llama_eagle3.py,sha256=_wnljvb8lLCQ0Z3Vuw0QI7F6b41x6I1WuvstZWGvCYE,13051
+tpu_inference/models/jax/llama_guard_4.py,sha256=R4wo45s1JsVD39t8JeAItujGoi-sl43HBH95hr7qEVw,15845
+tpu_inference/models/jax/qwen2.py,sha256=bart2yYGv0J-lNbk8Hk5jn5IF6j_Jp8YKSEjwVU_y24,14038
+tpu_inference/models/jax/qwen2_5_vl.py,sha256=3g3tUt7c83fKOdiMzuq2VyldCyeXoCBGrVYfqyIWwGE,50370
+tpu_inference/models/jax/qwen3.py,sha256=jVOOVrBFnxRIZ_Euo90iCga8rORpz0Kqs79uKqsFwEQ,11678
+tpu_inference/models/jax/utils/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/models/jax/utils/file_utils.py,sha256=8iZcGNvF1N0gNioH8fBlVYTSGYn4fC2WvmlTyeDZyZM,3415
+tpu_inference/models/jax/utils/multi_modal_utils.py,sha256=c2LRXdOPi3F779yg2UX-DnuFDxF1JciTcFa09iODxZs,6695
+tpu_inference/models/jax/utils/weight_utils.py,sha256=0xyjGlDSrA09gtb4plw9yX57VPMgn3o5WNl6mXPDU70,23121
+tpu_inference/models/jax/utils/qwix/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/models/jax/utils/qwix/qwix_utils.py,sha256=JOl3j4YO0P90ue0vsy-ZzNVGluh-VslAMOI-9wb1Igw,29288
+tpu_inference/models/vllm/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/models/vllm/vllm_model_wrapper.py,sha256=G4ClHbvMY0gPpTOFWStb1mEVVMzIc3-wz1KXC-mDpj8,13023
+tpu_inference/models/vllm/vllm_model_wrapper_context.py,sha256=vsXQnC2aZ_mHKb-7d9UeN28lfawfApNTm5asUMgEhgo,1762
+tpu_inference/platforms/__init__.py,sha256=BK6rwAhiqVSAUJ9m9EehSKetA6hEPe92flD9Ei076WQ,649
+tpu_inference/platforms/tpu_platform.py,sha256=bGTH1k0GI5AB_He5IghJtPwuyrhceUQ-rHs41fMpwhI,9826
+tpu_inference/runner/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/runner/block_table.py,sha256=K3Ic8EgPM08d_C5nEN60mxoRydlaQWySAemf_8Q_qVw,4175
+tpu_inference/runner/compilation_manager.py,sha256=BFjOzJUyEJTmUZAvGCm3yeqoY7Kkw2JKc_A3CzRoN7o,42112
+tpu_inference/runner/input_batch.py,sha256=bx221NX2IOWzrtopss-B-2ZKW4y-U6nQpG09PjpUziw,18273
+tpu_inference/runner/kv_cache.py,sha256=xpB6VTrT3lIq5JNNPJTVEnHFgehIzgxKNIHxxXIxwKI,6046
+tpu_inference/runner/kv_cache_manager.py,sha256=Bd5nMH-KupjeuDpn9pHdV4NzZ7inVa-bSrVGF3AYgRo,23417
+tpu_inference/runner/lora_utils.py,sha256=DGV_8aMrqb6Q4v7eC0UvipsM-6XQSt1afiZGKTKd6sc,4418
+tpu_inference/runner/multimodal_manager.py,sha256=dQm0sQ9nGHaWRS8rVPDBZP4P6jNFcJPufnAxv8DoWYs,10344
+tpu_inference/runner/persistent_batch_manager.py,sha256=aCeTyqCgBnQy_6hXjiNLtF81ekG0-YwlQiWeJhx-pdM,13838
+tpu_inference/runner/speculative_decoding_manager.py,sha256=-eSxTIGXbRWRZjHJfikb7kfqbtr_cj7Pca9zInWSn1w,10790
+tpu_inference/runner/structured_decoding_manager.py,sha256=sj1fPrit0qdhcQtDbue5kpxos7zL16_dZQ5YSXTDbzg,4148
+tpu_inference/runner/tpu_runner.py,sha256=djG7LKp69B_tCfsbHB7DrYncxRlB8tUnzNCyL8GYs9s,80656
+tpu_inference/runner/utils.py,sha256=lKqL5nxGTk7ufzJRNdp4udn2bPu3jIX52W7akXgSrHc,17133
+tpu_inference/spec_decode/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/spec_decode/jax/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/spec_decode/jax/eagle3.py,sha256=5WtEbkgzXpmFz374ibQD5IIcRro4d0SNeCYgBv2nM1c,19678
+tpu_inference/worker/__init__.py,sha256=Q9FlRO2IfSE9yEaiAYzWkOMBJPCaNYqh4ihcp0t0BQs,574
+tpu_inference/worker/tpu_worker.py,sha256=ntwCibPyiw-z8aMUdtu8usqU_q2b0u7diWNOmpjG_6o,21651
+tpu_inference-0.13.0rc2.post7.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+tpu_inference-0.13.0rc2.post7.dist-info/METADATA,sha256=1ZAhQLtZULopCk6yhmIPAlNwXWf3Yz4qbtwT_nRkN3Q,5881
+tpu_inference-0.13.0rc2.post7.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+tpu_inference-0.13.0rc2.post7.dist-info/top_level.txt,sha256=gb1hRIQ3DOawUfVzvPL2E__2KPIl9I0vb5r0xcRBGYQ,20
+tpu_inference-0.13.0rc2.post7.dist-info/RECORD,,

tpu_inference/models/jax/utils/quantization/configs/fp8_all_modules_w_only.yaml

@@ -1,5 +0,0 @@
-qwix:
-  rules:
-    # NOTE: each entry corresponds to a qwix.QuantizationRule
-    - module_path: '.*'
-      weight_qtype: 'float8_e4m3fn'

tpu_inference/models/jax/utils/quantization/configs/fp8_default.yaml

@@ -1,6 +0,0 @@
-qwix:
-  rules:
-    # NOTE: each entry corresponds to a qwix.QuantizationRule
-    - module_path: '.*'
-      weight_qtype: 'float8_e4m3fn'
-      act_qtype: 'float8_e4m3fn'

tpu_inference/models/jax/utils/quantization/configs/int8_all_modules_w_only.yaml

@@ -1,5 +0,0 @@
-qwix:
-  rules:
-    # NOTE: each entry corresponds to a qwix.QuantizationRule
-    - module_path: '.*'
-      weight_qtype: 'int8'

tpu_inference/models/jax/utils/quantization/configs/int8_default.yaml

@@ -1,6 +0,0 @@
-qwix:
-  rules:
-    # NOTE: each entry corresponds to a qwix.QuantizationRule
-    - module_path: '.*'
-      weight_qtype: 'int8'
-      act_qtype: 'int8'

tpu_inference/models/jax/utils/quantization/mxfp4_utils.py

@@ -1,105 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
-
-import torch
-
-# MXFP4 constants
-MXFP4_BLOCK_SIZE: int = 32
-# Exponent-only e8m0 scale bias used by MXFP4 scales
-MXFP4_SCALE_BIAS: int = 127
-# Name used in config.json quantization_config["quant_method"]
-MXFP4_QUANT_METHOD: str = "mxfp4"
-
-# Precompute a small LUT once; move to device on demand (cheap 16-element copy)
-FP4_LUT = torch.tensor(
-    [
-        0.0,
-        0.5,
-        1.0,
-        1.5,
-        2.0,
-        3.0,
-        4.0,
-        6.0,  # 0b0000-0b0111
-        -0.0,
-        -0.5,
-        -1.0,
-        -1.5,
-        -2.0,
-        -3.0,
-        -4.0,
-        -6.0,  # 0b1000-0b1111
-    ],
-    dtype=torch.float32)
-
-
-def unpack_mxfp4(packed: torch.Tensor) -> torch.Tensor:
-    """Unpack uint8 (..., 16) -> fp4 values (..., 32) using low->high nibble order.
-
-    Returns float32 values corresponding to FP4 codebook entries.
-    """
-    assert packed.dtype == torch.uint8
-    low = packed & 0x0F
-    high = (packed >> 4) & 0x0F
-    idx = torch.stack([low, high], dim=-1).flatten(-2)
-    lut = FP4_LUT.to(packed.device)
-    return lut[idx.long()]
-
-
-def e8m0_to_fp32(u8: torch.Tensor) -> torch.Tensor:
-    """Convert e8m0 uint8 exponents to power-of-two scales using MXFP4_SCALE_BIAS.
-
-    Uses ldexp for exact power-of-two scaling: 1.0 * 2**(u8 - bias).
-    """
-    exponents = (u8.to(torch.int32) - int(MXFP4_SCALE_BIAS)).to(torch.int32)
-    ones = torch.ones_like(u8, dtype=torch.float32)
-    return torch.ldexp(ones, exponents)
-
-
-def dequant_mxfp4_to_bf16(blocks_u8: torch.Tensor,
-                          scales_u8: torch.Tensor) -> torch.Tensor:
-    """Dequantize MXFP4 blocks/scales into bfloat16 values.
-
-    Args:
-        blocks_u8: uint8 tensor shaped [..., Kb, 16], each byte holds 2 FP4 codes.
-        scales_u8: uint8 tensor shaped [..., Kb], exponent-only e8m0 per 32-value block.
-
-    Returns:
-        torch.bfloat16 tensor with last logical dimension K = Kb * 32.
-    """
-    if blocks_u8.dtype != torch.uint8 or scales_u8.dtype != torch.uint8:
-        raise ValueError(
-            f"Expected uint8 inputs, got blocks={blocks_u8.dtype}, scales={scales_u8.dtype}"
-        )
-    # Unpack FP4 codes to float32 values [..., Kb, 32]
-    fp4_vals = unpack_mxfp4(blocks_u8)  # (..., Kb, 32)
-    # Compute power-of-two scales and apply per block
-    scales = e8m0_to_fp32(scales_u8).unsqueeze(-1)  # (..., Kb, 1)
-    full = (fp4_vals * scales).reshape(*fp4_vals.shape[:-2],
-                                       fp4_vals.shape[-2] * MXFP4_BLOCK_SIZE)
-    return full.to(torch.bfloat16)
-
-
-def unpack_mxfp4_to_fp32(
-        blocks_u8: torch.Tensor,
-        scales_u8: torch.Tensor) -> tuple[torch.Tensor, torch.Tensor]:
-    """Decode MXFP4 packed blocks and e8m0 scales to float32 codes and scales.
-
-    Args:
-        blocks_u8: uint8 tensor shaped [..., Kb, 16], each byte packs two FP4 codes.
-        scales_u8: uint8 tensor shaped [..., Kb], exponent-only e8m0 per block.
-
-    Returns:
-        (codes_fp32, scales_fp32), where
-        - codes_fp32 has shape [..., Kb*32] and dtype float32
-        - scales_fp32 has shape [..., Kb] and dtype float32
-    """
-    if blocks_u8.dtype != torch.uint8 or scales_u8.dtype != torch.uint8:
-        raise ValueError(
-            f"Expected uint8 inputs, got blocks={blocks_u8.dtype}, scales={scales_u8.dtype}"
-        )
-    fp4_vals = unpack_mxfp4(blocks_u8)  # (..., Kb, 32) float32
-    codes_fp32 = fp4_vals.reshape(*fp4_vals.shape[:-2],
-                                  fp4_vals.shape[-2] * MXFP4_BLOCK_SIZE)
-    scales_fp32 = e8m0_to_fp32(scales_u8)  # (..., Kb) float32
-    return codes_fp32, scales_fp32

tpu_inference-0.11.1.dev202511270815.dist-info/RECORD

@@ -1,174 +0,0 @@
-tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tests/test_base.py,sha256=Ct5WFRMHL7IHEIxk8FrzAvO8m0xFuDpzDBKkAKKAL2Q,7341
-tests/test_envs.py,sha256=Woyfp_d5HS-uTGo4_u9dYlBbgmhfIEoFb-Rx_k7YXD4,6298
-tests/test_quantization.py,sha256=IT5ASyS1uuWcxc22kRtBcA-V4j3Z3hb7pMztm3GOlBs,34445
-tests/test_tpu_info.py,sha256=ZrwlMsp8ffITkS_b8Q1t_QG-a-WVAd4NUcjHhGibcsI,4670
-tests/test_utils.py,sha256=Mta5ZzYCgRAh1-BjcOvvx9iQ9DnnXLps7oDHxVQp2yE,8236
-tests/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tests/core/test_core_tpu.py,sha256=r496rk1eOsK_F4nvm9zprl_T-RcO6eCUb7LuVReOZno,21413
-tests/core/test_disagg_executor.py,sha256=QdE2YZs08EyDDCmSjhiXkXqQ9BJTgO6csr_E1xkkfSg,2256
-tests/core/test_disagg_utils.py,sha256=alktTGppaGdg-_un0Amz8Y0IDQz-xNJN0dXG-YApEmY,1955
-tests/core/test_dp_scheduler.py,sha256=IwCR1Vs96V4CQdWA051rNaYxxr2V_byA1yx9HWyRoMg,37339
-tests/core/test_init.py,sha256=NEFI5A9eKGu4rmeJ2iqd0EmhlA3bzbVkXmMi1PV1b9U,1687
-tests/kernels/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tests/kernels/fused_moe_v1_test.py,sha256=sQ6gvpti94fpPYrSZn7frPPNjqbVmRibFtenVrGGCA4,10403
-tests/kernels/mla_v1_test.py,sha256=oZc4TCgquiG0KOeWfv46yJbUIpro_CgCMFc7vzyB7t8,11646
-tests/kernels/quantized_matmul_kernel_test.py,sha256=od5-zXFjcsc_gWGRDrREL8E_ftymNniQVTzgtkBo_Gc,5679
-tests/kernels/ragged_kv_cache_update_v2_test.py,sha256=6-HjP5CoUG-kcuP8MS-JJVMiBnPRo_zadS3VInnO0D4,10821
-tests/kernels/ragged_paged_attention_kernel_v2_test.py,sha256=pWqo9UYF0tzwgBKO_xYw-TYSPrtAsKcMK5Haj8hFG7I,11340
-tests/kernels/ragged_paged_attention_kernel_v3_hd64_test.py,sha256=JhIElqUZIRqIsfQ3U1RUzSiH_gz_SabAqDosGGZ2tlA,16321
-tests/kernels/ragged_paged_attention_kernel_v3_test.py,sha256=Hrd8iUkS1pS3rxeTyY53aYRg_ZL_d3NqgBXvOgnigSU,14838
-tests/lora/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tests/lora/conftest.py,sha256=EXjwE1CjmUUlMEXpyE3UwxvgrKUllE73I8BNKfP1FTc,984
-tests/lora/test_bgmv.py,sha256=gQxWsJdNX2nkrE2xyrG0exwf3E2eHm2k2nkEXoANuQc,1359
-tests/lora/test_layers.py,sha256=6B4HhMAItQmt0hPAQgyXgwSYs7b3bIbUf6LaPsqXLzY,25923
-tests/lora/test_lora.py,sha256=wJiF1P1BDnPN8TLX2tlFtdZ_QCkV-S9nPl6_uR6DqFc,4439
-tests/lora/utils.py,sha256=rY0tDZEZe58ye4-ykwrTnsiWuLcaEG57N_Rua90bDXI,2726
-tpu_inference/__init__.py,sha256=p4MaepRdN7723FUNE-3pOMxZWjFn4_TVFgjrNyty4JE,2304
-tpu_inference/env_override.py,sha256=pmL7lfs_rGCP92ya3wuWuudsCYeOMZ6tFZY82A4KkQc,365
-tpu_inference/envs.py,sha256=hoPuT0SyLCxqyZ0QJIha6EXSZv2TpACfmENuiT0iJMM,3956
-tpu_inference/logger.py,sha256=HQCz7NefmbturuhOC7-3Ixbtcdgoz4g9FHh2RB6o8cc,334
-tpu_inference/tpu_info.py,sha256=3iilHRQSFjwMJwhKcuuawTm7mhwkgHbj4zi6CiAySrs,2265
-tpu_inference/utils.py,sha256=Ddsx2CY2ARe46RZL27URzXCN3P6pMcKWB-APXUB8sHs,10098
-tpu_inference/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/core/core_tpu.py,sha256=WDD3koE_j1QhWS2BbMA2aQOZayPZm4tYPvzL4YCX2jY,33294
-tpu_inference/core/disagg_executor.py,sha256=HZpgYMVxRxm0RQxO4l8IDYBWJ6Z3Tac6xavc5otcirc,4657
-tpu_inference/core/disagg_utils.py,sha256=lv8MAVoAjtcmTaenUXVokg2q3d0tzsma86UiQlQ3omY,1492
-tpu_inference/core/sched/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/core/sched/dp_scheduler.py,sha256=mKs8Ms46szdlBfo8hjdqis2ZKAZbcKnHAGfEr0X5R8g,22527
-tpu_inference/distributed/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/distributed/jax_parallel_state.py,sha256=5_xCwcL03lFPUoSO_OP7hIVKpUFroW1m-jVO7R6FbUc,2223
-tpu_inference/distributed/tpu_connector.py,sha256=w_gOI6hX7NWefaxN_9XH9TXReGElOyFifdDHpPswotM,29696
-tpu_inference/distributed/utils.py,sha256=1KIREn28Zg10O-MSUkVQMRzS09WoGc_VLGOX4QTFJac,1504
-tpu_inference/executors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/executors/ray_distributed_executor.py,sha256=emYfSFJ3kluEmi6mlfnvxSUrC_mGVRVcjrUqUH2MR4g,16122
-tpu_inference/experimental/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/experimental/llama3_jax_stashed.py,sha256=YK1oSIfto9ALo-HB45XfSrbq9XgVbE4m2C-9zRwmSzI,10913
-tpu_inference/kernels/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/kernels/collectives/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/kernels/collectives/all_gather_matmul.py,sha256=0OYLLjlDmkRYScl7lHRi0o___5I5iMiW1gso-_dWSbc,27255
-tpu_inference/kernels/collectives/all_gather_matmul_tuned_block_sizes.py,sha256=KdaOIzTfIgUR0CcUTA46tpYH-cxPNoJx2cTMEvHx-Ac,1399
-tpu_inference/kernels/collectives/util.py,sha256=LbLD6lOxuszbUsykF89gWQqEJUICCZsfzam3EJDPnFE,1859
-tpu_inference/kernels/flash_attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/kernels/flash_attention/kernel.py,sha256=n8gmAFVfchMXlyaSEj8xXJm6AadFt26edQihPRdithY,25897
-tpu_inference/kernels/fused_moe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/kernels/fused_moe/v1/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/kernels/fused_moe/v1/kernel.py,sha256=xVXfclgbw_3U7c5W1azDFkFDK5FolBzDN9IL0rIzLQs,62813
-tpu_inference/kernels/mla/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/kernels/mla/v1/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/kernels/mla/v1/kernel.py,sha256=dw1nhpL47uQxMFOIN2kENC6aITbalT81YZLAyr1usLU,51571
-tpu_inference/kernels/quantized_matmul/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/kernels/quantized_matmul/kernel.py,sha256=4oEVUXgWOeOY-PfySHf-iEuUSd9J7GQk_rDSbxa7CXg,14086
-tpu_inference/kernels/quantized_matmul/tuned_block_sizes.py,sha256=3zhIm73JEE8qOty2_0v3AJlVz13k6qMB5wlXBDyC1EM,35130
-tpu_inference/kernels/quantized_matmul/util.py,sha256=rf6nIiAj9I2cj4LDvtaZGhcLXEc94o2xgMWasnFaREM,1943
-tpu_inference/kernels/ragged_paged_attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/kernels/ragged_paged_attention/v2/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/kernels/ragged_paged_attention/v2/kernel.py,sha256=OiQGAHhyggbp1PeuasPymopFohKOJjGXcpq9p_S8UWA,34940
-tpu_inference/kernels/ragged_paged_attention/v2/ragged_kv_cache_update.py,sha256=vGp2ZWODTbjyG9z2z0Qf_BX-wYHd5bUybnc_DtOz0nI,10995
-tpu_inference/kernels/ragged_paged_attention/v2/tuned_block_sizes.py,sha256=mw80bXBGenroGdrITV0F_EaI2s-Z9KWwqU9WodvJg14,97919
-tpu_inference/kernels/ragged_paged_attention/v3/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/kernels/ragged_paged_attention/v3/kernel.py,sha256=O179Fft5KpuN5LIFx3SghWXJJUqh3Og-xqfO4Z8QXYU,57032
-tpu_inference/kernels/ragged_paged_attention/v3/kernel_hd64.py,sha256=X_d-SMGNc3zv396uQGL-73oLzp5ZQP8gaubMDebM_AY,57426
-tpu_inference/kernels/ragged_paged_attention/v3/tuned_block_sizes.py,sha256=k3LwduhZO85cJ-pSgnGN0c2Nn8eNeQq4eA94KUXJzMw,142198
-tpu_inference/kernels/ragged_paged_attention/v3/tuned_block_sizes_hd64.py,sha256=P3_ivi8iUz5QMU_3pgpl4Bkbmn0q0NpDtVJX39haRQA,11208
-tpu_inference/kernels/ragged_paged_attention/v3/util.py,sha256=1N_ozjKboDYLteFJndWoLXNudj2z53rGXMkELa5Z9tY,1102
-tpu_inference/layers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/layers/common/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/layers/common/attention_interface.py,sha256=SQZ-1I32Jqg7GGI-z4BVibXbaitJHyTs26X3B5nBRVo,13369
-tpu_inference/layers/common/attention_metadata.py,sha256=St8ZatbY1D7xQACKJH459jMgp3oTP3AQ36mi9FZdrPU,850
-tpu_inference/layers/common/binary_search.py,sha256=ZQi-z1wG6WTcfVQXeTGOZokX4K1DSf9kCzqfrhEU8lk,12320
-tpu_inference/layers/common/quant_methods.py,sha256=mQSxZ44-QQtm22C_8ViejnP1cP2Dv6yc2YaP6oMKJeQ,185
-tpu_inference/layers/common/sharding.py,sha256=KUPd5HxfmQZ01wc3lGEusI6QYHnZxFp7-Ur-0b8hOH8,25256
-tpu_inference/layers/jax/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/layers/jax/base.py,sha256=Vhts6ZMwNCZ8LbnEXeB0rl3nHdS5hDJWX7HEa7Fl7yE,5775
-tpu_inference/layers/jax/constants.py,sha256=NcYg0zAf3ClfP7YMYdYu_F1GngOzZaIxIAHBZDunKw4,2755
-tpu_inference/layers/jax/layers.py,sha256=yv_lC2tbJuzVL-OaXYooX82Ys8hWZATeH9M78coJ3VI,10633
-tpu_inference/layers/jax/misc.py,sha256=znKv1Nuq_LgYpaIu0qlzUVDgQWnjjG7aqPJGM8kuwcw,566
-tpu_inference/layers/jax/rope.py,sha256=i2E7pRLWgOaFLbeo8_phZwKQWJW7ohAyl69E2V2Mc2U,11349
-tpu_inference/layers/jax/rope_interface.py,sha256=X0SruXizlCHGnssFujC1pL07UC4Vsp7-gdBy_Q7JZhI,8375
-tpu_inference/layers/jax/transformer_block.py,sha256=ufv-yfVDmRP_Ynrx3UX9xj-x0PkNw_tQ-0N0eYf4i7M,3917
-tpu_inference/layers/jax/attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/layers/jax/attention/attention.py,sha256=DJFDkpQc9SDD156wVPFw3r2XaBgb44QNJ8OcdONaF5g,10085
-tpu_inference/layers/jax/attention/deepseek_v3_attention.py,sha256=YlagoBMwINv2KRH1dr4oEcH_cQ9QMPB55nO2FQZsWs0,14010
-tpu_inference/layers/jax/attention/gpt_oss_attention.py,sha256=rkrEv4aNZxtAGcXd1HXHUxhNeDNAd9nWTEZOKWSI8cA,8725
-tpu_inference/layers/jax/attention/llama4_attention.py,sha256=VvUmfBxQEbHf3F2BrcYDUnq5abj7CSDYeRsNx_eVAh0,6162
-tpu_inference/layers/jax/moe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/layers/jax/moe/deepseek_v3_moe.py,sha256=Q6CuwwiZtWYm6iUee1wJoDJrwJE6_bcznTK2HrtXb0M,26089
-tpu_inference/layers/jax/moe/gpt_oss_moe.py,sha256=Rx5b1jg2XMm7Xx9hrjgvyhscaJ_zGbVMHmeEiLh7kIQ,6196
-tpu_inference/layers/jax/moe/moe.py,sha256=cA8R1rjbBwNEoNlsPWjeIBB9nvaRDwlEdwQTVg6lTpY,8762
-tpu_inference/layers/jax/sample/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/layers/jax/sample/rejection_sampler.py,sha256=nI5s0E73xkqDIu2hTljIXt23B1Q-gRnC1myoQpGDJrQ,20426
-tpu_inference/layers/jax/sample/sampling.py,sha256=C30KgmdOVSaagvHhbfLgVJtVQmJo86CbHPa4h36Vn70,3314
-tpu_inference/layers/jax/sample/sampling_metadata.py,sha256=Gd835LNWfGM0NRQBVBqEv0nPwt5q9F4AdFym0CUS1fw,2561
-tpu_inference/layers/vllm/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/layers/vllm/attention.py,sha256=wbJpcgqEAuIirv5PIULbiP-ggMKjmTanbB7Dg0BVYv4,7366
-tpu_inference/layers/vllm/fused_moe.py,sha256=5rzPzMsKRmsD-hh2Rue0ahaeyhh6cHB7FUIrKfn4s0U,21089
-tpu_inference/layers/vllm/linear_common.py,sha256=_YlJtbdaYcck_j-gFLos_k0ycktVWxT8Qo57tR2YqJ8,7749
-tpu_inference/layers/vllm/sharding.py,sha256=as7CF8UKTF3ToymwRY5Pi8uzwJk0P1sHPkWB5xEx3mA,9169
-tpu_inference/layers/vllm/quantization/__init__.py,sha256=SEppGayBzzQ5tsXLSy99aqilkAawQwYxnv2alCg6-ZU,1777
-tpu_inference/layers/vllm/quantization/awq.py,sha256=-8ZmjGvSKJB6_JuwSctNWt8xHWq4VSvK_AK9iahlgCo,8495
-tpu_inference/layers/vllm/quantization/common.py,sha256=8XD64pPa077c9HThFhLFVHlDL9YBafnYwp6rp6gR44E,4432
-tpu_inference/layers/vllm/quantization/mxfp4.py,sha256=3T3M0qLoW7GKdqbv_toMoQP39lV1qCoQ8Uc8l8aq1hg,14495
-tpu_inference/layers/vllm/quantization/unquantized.py,sha256=nSRBzVurTiQQkF9FuSTshfRwfxfzs54E2_4eK7Eyhj0,15345
-tpu_inference/layers/vllm/quantization/compressed_tensors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/layers/vllm/quantization/compressed_tensors/compressed_tensors.py,sha256=6idEyy3e849fZ1UeNvc9eSHYX7e6qvohrJa_d_D9MBk,5285
-tpu_inference/layers/vllm/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=FM901QhyhJRC8CuMeICzCVVERvBHbhruRxYW0EQ570s,8820
-tpu_inference/layers/vllm/quantization/compressed_tensors/schemes/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/layers/vllm/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py,sha256=6sQvsxiWdi5Vte8V9vrQ2abaqGqWpq-mtzU7lGAo-ac,8759
-tpu_inference/layers/vllm/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_int8.py,sha256=4y7lYgybpXszpCAtxGFhR8LDEbEoCCeo3DfUSOXxhaQ,5202
-tpu_inference/lora/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/lora/torch_lora_ops.py,sha256=pr3N7DVfkn3ANijUC6dBoiCtIJW4fdJpKdC3zWBUsxE,3121
-tpu_inference/lora/torch_punica_tpu.py,sha256=qTnXZGLoOgvukSxeunO_SfpPTlkq9GlMj9H7zVYg9LE,12680
-tpu_inference/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/models/common/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/models/common/model_loader.py,sha256=_eFPCM0_ssjoVdj38rMLR-qnJ7iW_Ox_hc8JiWycxNs,19923
-tpu_inference/models/jax/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/models/jax/deepseek_v3.py,sha256=SKOHVEC-_2NLxBnzBzbu5tu0d6FTlAEiI1EefGaO2QE,40047
-tpu_inference/models/jax/gpt_oss.py,sha256=Vw4LRB5Kp6hbA2hjZGFS8kiEqOCjf881XH2JNtu2S1I,20924
-tpu_inference/models/jax/jax_intermediate_tensor.py,sha256=Pxu1PCV5LN5X58aYVkPiohcXZIeKVim2oqvrS_cVgw4,2604
-tpu_inference/models/jax/llama3.py,sha256=ZiFtrpAzXTT9vAPES9UeuJInCWGbvDWs7g0_JLdCCa4,13479
-tpu_inference/models/jax/llama4.py,sha256=wf2Sp2iYViaYD5rSfv3_ryO6gYuYM5XaOyvghaP4OCY,29631
-tpu_inference/models/jax/llama_eagle3.py,sha256=7-U99yvBkle-FSZ3NDDI-obWSQ2Fo2OTOi1H67H4jxY,12476
-tpu_inference/models/jax/llama_guard_4.py,sha256=LrnU2zBWM0s4q_5dwmR--OO0V7ttltsYhrHYlBgQVIw,15275
-tpu_inference/models/jax/qwen2.py,sha256=SuAp7tErk8OoIRko0Vt6QSOZP_9B9r5GTfqmVfImUIo,13410
-tpu_inference/models/jax/qwen2_5_vl.py,sha256=WUOmqNE6fHQ8PGU85Y8Bt6-CtCC1Uubbox_9FdpDMMo,49833
-tpu_inference/models/jax/qwen3.py,sha256=CIZQKjZDke_LPGsLNhRCJdDTzWueUneBPAQ1blS24IM,11050
-tpu_inference/models/jax/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/models/jax/utils/file_utils.py,sha256=NOuSC3YFnZpf3CZgYdghbbiNYJt42zgjlEYbOZIVct4,2840
-tpu_inference/models/jax/utils/multi_modal_utils.py,sha256=rrIrQWidkUnGilBHKNpdYh7_2BkvnAaqanXjC81GNcg,6156
-tpu_inference/models/jax/utils/weight_utils.py,sha256=qFU53jPHPvIcs_EOdIH80oNojpUp7GdSY2E6NZNsjvM,21376
-tpu_inference/models/jax/utils/quantization/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/models/jax/utils/quantization/mxfp4_utils.py,sha256=boGnqJCRIOf5nedAxQ8_IUTV6Rfll10DXnRC40BeeE8,3682
-tpu_inference/models/jax/utils/quantization/quantization_utils.py,sha256=xgKoKB7AM3TYPxzVgEGLTK9ebQH2Kx8mNuO0heovkmk,26778
-tpu_inference/models/jax/utils/quantization/configs/fp8_all_modules_w_only.yaml,sha256=d_YHPtaRJ_7PBrPijSzJGnVeoJO62tKIGqrgFqpYT1k,137
-tpu_inference/models/jax/utils/quantization/configs/fp8_default.yaml,sha256=b7SyL75HuSTj3fN9_ZLCK_CDiccL5DGq_DddGmxj_qk,170
-tpu_inference/models/jax/utils/quantization/configs/int8_all_modules_w_only.yaml,sha256=0Qwij71zj9k6rmrUNd8Q5df9YYfkoJ1ZkgMAHxQy81k,128
-tpu_inference/models/jax/utils/quantization/configs/int8_default.yaml,sha256=lGec0UwwxmNPNgKPSsTsCMSXNJjhw507KMtM2NsSCMw,152
-tpu_inference/models/vllm/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/models/vllm/vllm_model_wrapper.py,sha256=Cfsd0PjuR-hCoiCwPVdzjkE6AmHLYY1JQyBERyFkl-E,12344
-tpu_inference/models/vllm/vllm_model_wrapper_context.py,sha256=yxlJHPmRQIAwlb1MmHK3xfXokgIkJ-evNU4PgyoJUdg,1187
-tpu_inference/platforms/__init__.py,sha256=lQCrKddS_GcGpCbeogvz9zOZD1mQw5bBsiw8On46qFQ,74
-tpu_inference/platforms/tpu_platform.py,sha256=W_19FvlFxPs0V0vcr3NI6oVBG-eA3eBV2-H0Cr3Kyco,10879
-tpu_inference/runner/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/runner/block_table.py,sha256=K3Ic8EgPM08d_C5nEN60mxoRydlaQWySAemf_8Q_qVw,4175
-tpu_inference/runner/compilation_manager.py,sha256=DR5TkHGin2QbRIWZlkkD5sUdxonTgr35pMYyrSwGk_U,37585
-tpu_inference/runner/input_batch.py,sha256=bx221NX2IOWzrtopss-B-2ZKW4y-U6nQpG09PjpUziw,18273
-tpu_inference/runner/kv_cache.py,sha256=F4dzW2d53xuxkFUn0oKzwE6VklGUeVm-QM19NVfIQDU,4577
-tpu_inference/runner/kv_cache_manager.py,sha256=2iwEc1vXt-p8kkKByvlqy4IKi5bOqFpOlrq0QmHHnQA,22450
-tpu_inference/runner/lora_utils.py,sha256=B4xMCgXGJ4VNdePvn89HH3tIZ-gYsQ7Vq_YCiYIATEY,3843
-tpu_inference/runner/multimodal_manager.py,sha256=azEPdHOwz8CN11MQmorGdtrCLbFaTCxdWyuEsZTzjYM,9778
-tpu_inference/runner/persistent_batch_manager.py,sha256=KERSfKy6XjMejnbtPGI3hzoYAHJLeCxmpZVYPqBCago,11156
-tpu_inference/runner/speculative_decoding_manager.py,sha256=I3FDWKh2dn6nV8LgTGfCTwMKYnxQsTPpBIrmaJngXHs,10215
-tpu_inference/runner/structured_decoding_manager.py,sha256=gZQKQUFxh6xYYH9eGTdbguqk8hc2WwTrIdMMuCcbymE,3573
-tpu_inference/runner/tpu_runner.py,sha256=A5Ed4NL6CPNv7o7u6zqmdPbmmPyiIxFcwWlJ0E5_fpU,77991
-tpu_inference/runner/utils.py,sha256=ZnWUoNo-7INeB0mdXti1jwUOdbmxyExznOs-crRTQLk,17126
-tpu_inference/spec_decode/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/spec_decode/jax/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/spec_decode/jax/eagle3.py,sha256=ci-yPOSlAfsuwoR_QAGrywtDLMbicjOhl787o9MahYg,17376
-tpu_inference/worker/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tpu_inference/worker/tpu_worker.py,sha256=4QH83MzYCnubwWXTvPEc2BmiU2R5KILci6PawDNpnHM,20670
-tpu_inference-0.11.1.dev202511270815.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-tpu_inference-0.11.1.dev202511270815.dist-info/METADATA,sha256=nAfRlJUVGJkVnroEwrw0EsiO9CqWJLrGgHkt5AORBJk,5517
-tpu_inference-0.11.1.dev202511270815.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-tpu_inference-0.11.1.dev202511270815.dist-info/top_level.txt,sha256=gb1hRIQ3DOawUfVzvPL2E__2KPIl9I0vb5r0xcRBGYQ,20
-tpu_inference-0.11.1.dev202511270815.dist-info/RECORD,,