diff --git a/qwen3_6_scripts/cccl_preload/libcccl_allocator.so b/qwen3_6_scripts/cccl_preload/libcccl_allocator.so new file mode 100755 index 00000000..5de35903 Binary files /dev/null and b/qwen3_6_scripts/cccl_preload/libcccl_allocator.so differ diff --git a/qwen3_6_scripts/prebuilt/corex-3.2.3-ivcore10/SHA256SUMS b/qwen3_6_scripts/prebuilt/corex-3.2.3-ivcore10/SHA256SUMS index 7360f63e..043316d5 100644 --- a/qwen3_6_scripts/prebuilt/corex-3.2.3-ivcore10/SHA256SUMS +++ b/qwen3_6_scripts/prebuilt/corex-3.2.3-ivcore10/SHA256SUMS @@ -3,11 +3,12 @@ ad4ea7707bb2f2bfe04e07a7ad5fd58a647232be70a3056937a0d738c8254bff corex_fused_paged_prefill.so 1856c86e3100415061aa698a48bdeff3fe785994b45b4e72a42cd9158552a7d8 corex_gdn_beta_decay.so 957c7518f5831299fc73f19a4ca2aa3c8231afe9ea7c979127b4f426cd9d6906 corex_gdn_causal_conv.so +ff1c1c67ec252ed993bf1840a33ef5c4b386b730ba6dc5bf995991013c226222 corex_gdn_chunk_recurrent.so ec2d11fa82d9d0816a6da53e62605e962786fa20ecd5f62e50f9d43087fc4d67 corex_gdn_gated_norm.so 27b7ae2ce4fe173336355d72a2678d043df4bd1ed85e9231a99bfb81885a6ce3 corex_gdn_packed_decode.so 015b61046ad73d8f12d754f7a87d4f6cba33070af1c079879e15b71a94571670 corex_gdn_qk_map.so 0eb120e89608bb5b64ca4356a5d3d362121806d081ccc1ccf346dac472a819ec corex_moe_direct_routed.so d26f2fa39c3921a95793786601e90cf6ebadd06f1d752af541bf82c21acbc1c9 corex_moe_exact_reduce.so +c3208c8e0c13f54dbe22a9cfc88bdc6ab040e920d6cae4bc0ecf7087880795f3 corex_moe_topk_softmax.so 50b0b44c1da779bb2c03419ed549aee9bb922d1f9bab8b7f11a3d91cca0d21c3 corex_moe_weight_gather.so e944ec0528ed9b6cb74518de3c57e3730543a7bdebc872f993bfdc8424f13e6b corex_paged_kv_gather.so -c3208c8e0c13f54dbe22a9cfc88bdc6ab040e920d6cae4bc0ecf7087880795f3 corex_moe_topk_softmax.so diff --git a/qwen3_6_scripts/prebuilt/corex-3.2.3-ivcore10/corex_gdn_chunk_recurrent.so b/qwen3_6_scripts/prebuilt/corex-3.2.3-ivcore10/corex_gdn_chunk_recurrent.so new file mode 100755 index 00000000..21a5c8db Binary files /dev/null and b/qwen3_6_scripts/prebuilt/corex-3.2.3-ivcore10/corex_gdn_chunk_recurrent.so differ diff --git a/vllm/__pycache__/__init__.cpython-310.pyc b/vllm/__pycache__/__init__.cpython-310.pyc index ba64550a..e28db63e 100644 Binary files a/vllm/__pycache__/__init__.cpython-310.pyc and b/vllm/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/__pycache__/_core_ext.cpython-310.pyc b/vllm/__pycache__/_core_ext.cpython-310.pyc index 3c7a3da7..e2ba9d95 100644 Binary files a/vllm/__pycache__/_core_ext.cpython-310.pyc and b/vllm/__pycache__/_core_ext.cpython-310.pyc differ diff --git a/vllm/__pycache__/_custom_ops.cpython-310.pyc b/vllm/__pycache__/_custom_ops.cpython-310.pyc index fc17fb1a..20ce3a0e 100644 Binary files a/vllm/__pycache__/_custom_ops.cpython-310.pyc and b/vllm/__pycache__/_custom_ops.cpython-310.pyc differ diff --git a/vllm/__pycache__/beam_search.cpython-310.pyc b/vllm/__pycache__/beam_search.cpython-310.pyc index 4e88877a..71af9c26 100644 Binary files a/vllm/__pycache__/beam_search.cpython-310.pyc and b/vllm/__pycache__/beam_search.cpython-310.pyc differ diff --git a/vllm/__pycache__/config.cpython-310.pyc b/vllm/__pycache__/config.cpython-310.pyc index 7f93840b..326d3e30 100644 Binary files a/vllm/__pycache__/config.cpython-310.pyc and b/vllm/__pycache__/config.cpython-310.pyc differ diff --git a/vllm/__pycache__/connections.cpython-310.pyc b/vllm/__pycache__/connections.cpython-310.pyc index 977dbbab..bbc9802a 100644 Binary files a/vllm/__pycache__/connections.cpython-310.pyc and b/vllm/__pycache__/connections.cpython-310.pyc differ diff --git a/vllm/__pycache__/envs.cpython-310.pyc b/vllm/__pycache__/envs.cpython-310.pyc index 223d6c0c..3aa9c44f 100644 Binary files a/vllm/__pycache__/envs.cpython-310.pyc and b/vllm/__pycache__/envs.cpython-310.pyc differ diff --git a/vllm/__pycache__/logger.cpython-310.pyc b/vllm/__pycache__/logger.cpython-310.pyc index 5009ecf4..09bc19a3 100644 Binary files a/vllm/__pycache__/logger.cpython-310.pyc and b/vllm/__pycache__/logger.cpython-310.pyc differ diff --git a/vllm/__pycache__/outputs.cpython-310.pyc b/vllm/__pycache__/outputs.cpython-310.pyc index 932e79bd..836ce4dd 100644 Binary files a/vllm/__pycache__/outputs.cpython-310.pyc and b/vllm/__pycache__/outputs.cpython-310.pyc differ diff --git a/vllm/__pycache__/pooling_params.cpython-310.pyc b/vllm/__pycache__/pooling_params.cpython-310.pyc index da6c1ba4..56a94a30 100644 Binary files a/vllm/__pycache__/pooling_params.cpython-310.pyc and b/vllm/__pycache__/pooling_params.cpython-310.pyc differ diff --git a/vllm/__pycache__/sampling_params.cpython-310.pyc b/vllm/__pycache__/sampling_params.cpython-310.pyc index 371575bd..1abf8352 100644 Binary files a/vllm/__pycache__/sampling_params.cpython-310.pyc and b/vllm/__pycache__/sampling_params.cpython-310.pyc differ diff --git a/vllm/__pycache__/scalar_type.cpython-310.pyc b/vllm/__pycache__/scalar_type.cpython-310.pyc index 5f2f2da9..5f053388 100644 Binary files a/vllm/__pycache__/scalar_type.cpython-310.pyc and b/vllm/__pycache__/scalar_type.cpython-310.pyc differ diff --git a/vllm/__pycache__/sequence.cpython-310.pyc b/vllm/__pycache__/sequence.cpython-310.pyc index de030385..0a4397df 100644 Binary files a/vllm/__pycache__/sequence.cpython-310.pyc and b/vllm/__pycache__/sequence.cpython-310.pyc differ diff --git a/vllm/__pycache__/tracing.cpython-310.pyc b/vllm/__pycache__/tracing.cpython-310.pyc index 0914d513..1e9f94d2 100644 Binary files a/vllm/__pycache__/tracing.cpython-310.pyc and b/vllm/__pycache__/tracing.cpython-310.pyc differ diff --git a/vllm/__pycache__/utils.cpython-310.pyc b/vllm/__pycache__/utils.cpython-310.pyc index 02651dec..ecbd7430 100644 Binary files a/vllm/__pycache__/utils.cpython-310.pyc and b/vllm/__pycache__/utils.cpython-310.pyc differ diff --git a/vllm/__pycache__/version.cpython-310.pyc b/vllm/__pycache__/version.cpython-310.pyc index 42f846be..fcb4caaf 100644 Binary files a/vllm/__pycache__/version.cpython-310.pyc and b/vllm/__pycache__/version.cpython-310.pyc differ diff --git a/vllm/adapter_commons/__pycache__/__init__.cpython-310.pyc b/vllm/adapter_commons/__pycache__/__init__.cpython-310.pyc index 10fe1680..5640e811 100644 Binary files a/vllm/adapter_commons/__pycache__/__init__.cpython-310.pyc and b/vllm/adapter_commons/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/adapter_commons/__pycache__/request.cpython-310.pyc b/vllm/adapter_commons/__pycache__/request.cpython-310.pyc index c5beddc2..93892cea 100644 Binary files a/vllm/adapter_commons/__pycache__/request.cpython-310.pyc and b/vllm/adapter_commons/__pycache__/request.cpython-310.pyc differ diff --git a/vllm/compilation/__pycache__/__init__.cpython-310.pyc b/vllm/compilation/__pycache__/__init__.cpython-310.pyc index 8f5fb174..39459fd0 100644 Binary files a/vllm/compilation/__pycache__/__init__.cpython-310.pyc and b/vllm/compilation/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/compilation/__pycache__/levels.cpython-310.pyc b/vllm/compilation/__pycache__/levels.cpython-310.pyc index 50e2e9f1..4d01310d 100644 Binary files a/vllm/compilation/__pycache__/levels.cpython-310.pyc and b/vllm/compilation/__pycache__/levels.cpython-310.pyc differ diff --git a/vllm/core/__pycache__/__init__.cpython-310.pyc b/vllm/core/__pycache__/__init__.cpython-310.pyc index 41f56883..739f5fe4 100644 Binary files a/vllm/core/__pycache__/__init__.cpython-310.pyc and b/vllm/core/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/core/__pycache__/interfaces.cpython-310.pyc b/vllm/core/__pycache__/interfaces.cpython-310.pyc index 7fed706c..8f954aaa 100644 Binary files a/vllm/core/__pycache__/interfaces.cpython-310.pyc and b/vllm/core/__pycache__/interfaces.cpython-310.pyc differ diff --git a/vllm/core/__pycache__/scheduler.cpython-310.pyc b/vllm/core/__pycache__/scheduler.cpython-310.pyc index 0f0d1917..c514172c 100644 Binary files a/vllm/core/__pycache__/scheduler.cpython-310.pyc and b/vllm/core/__pycache__/scheduler.cpython-310.pyc differ diff --git a/vllm/distributed/__pycache__/__init__.cpython-310.pyc b/vllm/distributed/__pycache__/__init__.cpython-310.pyc index 912dfd76..a6e0082f 100644 Binary files a/vllm/distributed/__pycache__/__init__.cpython-310.pyc and b/vllm/distributed/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/distributed/__pycache__/communication_op.cpython-310.pyc b/vllm/distributed/__pycache__/communication_op.cpython-310.pyc index 52ccfdc2..62c0c1bc 100644 Binary files a/vllm/distributed/__pycache__/communication_op.cpython-310.pyc and b/vllm/distributed/__pycache__/communication_op.cpython-310.pyc differ diff --git a/vllm/distributed/__pycache__/parallel_state.cpython-310.pyc b/vllm/distributed/__pycache__/parallel_state.cpython-310.pyc index f696dc6c..ca533991 100644 Binary files a/vllm/distributed/__pycache__/parallel_state.cpython-310.pyc and b/vllm/distributed/__pycache__/parallel_state.cpython-310.pyc differ diff --git a/vllm/distributed/__pycache__/utils.cpython-310.pyc b/vllm/distributed/__pycache__/utils.cpython-310.pyc index c4fac5b0..34cb00fc 100644 Binary files a/vllm/distributed/__pycache__/utils.cpython-310.pyc and b/vllm/distributed/__pycache__/utils.cpython-310.pyc differ diff --git a/vllm/engine/__pycache__/__init__.cpython-310.pyc b/vllm/engine/__pycache__/__init__.cpython-310.pyc index 20b1de9c..1551cee9 100644 Binary files a/vllm/engine/__pycache__/__init__.cpython-310.pyc and b/vllm/engine/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/engine/__pycache__/arg_utils.cpython-310.pyc b/vllm/engine/__pycache__/arg_utils.cpython-310.pyc index 93db9cb5..5e1985a0 100644 Binary files a/vllm/engine/__pycache__/arg_utils.cpython-310.pyc and b/vllm/engine/__pycache__/arg_utils.cpython-310.pyc differ diff --git a/vllm/engine/__pycache__/async_llm_engine.cpython-310.pyc b/vllm/engine/__pycache__/async_llm_engine.cpython-310.pyc index ecb32f47..39ae9e5c 100644 Binary files a/vllm/engine/__pycache__/async_llm_engine.cpython-310.pyc and b/vllm/engine/__pycache__/async_llm_engine.cpython-310.pyc differ diff --git a/vllm/engine/__pycache__/async_timeout.cpython-310.pyc b/vllm/engine/__pycache__/async_timeout.cpython-310.pyc index 1f080ed0..262eb076 100644 Binary files a/vllm/engine/__pycache__/async_timeout.cpython-310.pyc and b/vllm/engine/__pycache__/async_timeout.cpython-310.pyc differ diff --git a/vllm/engine/__pycache__/llm_engine.cpython-310.pyc b/vllm/engine/__pycache__/llm_engine.cpython-310.pyc index c106623e..4b9dfeda 100644 Binary files a/vllm/engine/__pycache__/llm_engine.cpython-310.pyc and b/vllm/engine/__pycache__/llm_engine.cpython-310.pyc differ diff --git a/vllm/engine/__pycache__/metrics_types.cpython-310.pyc b/vllm/engine/__pycache__/metrics_types.cpython-310.pyc index 0ed046f1..6333dd96 100644 Binary files a/vllm/engine/__pycache__/metrics_types.cpython-310.pyc and b/vllm/engine/__pycache__/metrics_types.cpython-310.pyc differ diff --git a/vllm/engine/output_processor/__pycache__/__init__.cpython-310.pyc b/vllm/engine/output_processor/__pycache__/__init__.cpython-310.pyc index d16adb25..5e7f46a6 100644 Binary files a/vllm/engine/output_processor/__pycache__/__init__.cpython-310.pyc and b/vllm/engine/output_processor/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/engine/output_processor/__pycache__/interfaces.cpython-310.pyc b/vllm/engine/output_processor/__pycache__/interfaces.cpython-310.pyc index 13ebd7df..87ff7e95 100644 Binary files a/vllm/engine/output_processor/__pycache__/interfaces.cpython-310.pyc and b/vllm/engine/output_processor/__pycache__/interfaces.cpython-310.pyc differ diff --git a/vllm/engine/output_processor/__pycache__/stop_checker.cpython-310.pyc b/vllm/engine/output_processor/__pycache__/stop_checker.cpython-310.pyc index c7789823..3747b52d 100644 Binary files a/vllm/engine/output_processor/__pycache__/stop_checker.cpython-310.pyc and b/vllm/engine/output_processor/__pycache__/stop_checker.cpython-310.pyc differ diff --git a/vllm/engine/output_processor/__pycache__/util.cpython-310.pyc b/vllm/engine/output_processor/__pycache__/util.cpython-310.pyc index 14ba774d..2ee93e86 100644 Binary files a/vllm/engine/output_processor/__pycache__/util.cpython-310.pyc and b/vllm/engine/output_processor/__pycache__/util.cpython-310.pyc differ diff --git a/vllm/entrypoints/__pycache__/__init__.cpython-310.pyc b/vllm/entrypoints/__pycache__/__init__.cpython-310.pyc index 8ebcd41a..87300de6 100644 Binary files a/vllm/entrypoints/__pycache__/__init__.cpython-310.pyc and b/vllm/entrypoints/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/entrypoints/__pycache__/chat_utils.cpython-310.pyc b/vllm/entrypoints/__pycache__/chat_utils.cpython-310.pyc index 37ddfb7f..f9a500ea 100644 Binary files a/vllm/entrypoints/__pycache__/chat_utils.cpython-310.pyc and b/vllm/entrypoints/__pycache__/chat_utils.cpython-310.pyc differ diff --git a/vllm/entrypoints/__pycache__/llm.cpython-310.pyc b/vllm/entrypoints/__pycache__/llm.cpython-310.pyc index 3f0bb4df..c67e7a0e 100644 Binary files a/vllm/entrypoints/__pycache__/llm.cpython-310.pyc and b/vllm/entrypoints/__pycache__/llm.cpython-310.pyc differ diff --git a/vllm/entrypoints/openai/__pycache__/__init__.cpython-310.pyc b/vllm/entrypoints/openai/__pycache__/__init__.cpython-310.pyc index d5f09d23..ed69a5d2 100644 Binary files a/vllm/entrypoints/openai/__pycache__/__init__.cpython-310.pyc and b/vllm/entrypoints/openai/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/entrypoints/openai/__pycache__/logits_processors.cpython-310.pyc b/vllm/entrypoints/openai/__pycache__/logits_processors.cpython-310.pyc index 45a3dbe6..d8c80f93 100644 Binary files a/vllm/entrypoints/openai/__pycache__/logits_processors.cpython-310.pyc and b/vllm/entrypoints/openai/__pycache__/logits_processors.cpython-310.pyc differ diff --git a/vllm/executor/__pycache__/__init__.cpython-310.pyc b/vllm/executor/__pycache__/__init__.cpython-310.pyc index a4435721..7908a153 100644 Binary files a/vllm/executor/__pycache__/__init__.cpython-310.pyc and b/vllm/executor/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/executor/__pycache__/executor_base.cpython-310.pyc b/vllm/executor/__pycache__/executor_base.cpython-310.pyc index 6c483d25..62c0ced4 100644 Binary files a/vllm/executor/__pycache__/executor_base.cpython-310.pyc and b/vllm/executor/__pycache__/executor_base.cpython-310.pyc differ diff --git a/vllm/executor/__pycache__/gpu_executor.cpython-310.pyc b/vllm/executor/__pycache__/gpu_executor.cpython-310.pyc index 8d7cc79c..046d7c02 100644 Binary files a/vllm/executor/__pycache__/gpu_executor.cpython-310.pyc and b/vllm/executor/__pycache__/gpu_executor.cpython-310.pyc differ diff --git a/vllm/executor/__pycache__/msgspec_utils.cpython-310.pyc b/vllm/executor/__pycache__/msgspec_utils.cpython-310.pyc index 9dd43909..7929228c 100644 Binary files a/vllm/executor/__pycache__/msgspec_utils.cpython-310.pyc and b/vllm/executor/__pycache__/msgspec_utils.cpython-310.pyc differ diff --git a/vllm/executor/__pycache__/ray_utils.cpython-310.pyc b/vllm/executor/__pycache__/ray_utils.cpython-310.pyc index 58e6d0d3..3f010a54 100644 Binary files a/vllm/executor/__pycache__/ray_utils.cpython-310.pyc and b/vllm/executor/__pycache__/ray_utils.cpython-310.pyc differ diff --git a/vllm/inputs/__pycache__/__init__.cpython-310.pyc b/vllm/inputs/__pycache__/__init__.cpython-310.pyc index 1ecbfd4b..f75d0687 100644 Binary files a/vllm/inputs/__pycache__/__init__.cpython-310.pyc and b/vllm/inputs/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/inputs/__pycache__/data.cpython-310.pyc b/vllm/inputs/__pycache__/data.cpython-310.pyc index 437d7329..8128f102 100644 Binary files a/vllm/inputs/__pycache__/data.cpython-310.pyc and b/vllm/inputs/__pycache__/data.cpython-310.pyc differ diff --git a/vllm/inputs/__pycache__/parse.cpython-310.pyc b/vllm/inputs/__pycache__/parse.cpython-310.pyc index 4664dc3c..55308de9 100644 Binary files a/vllm/inputs/__pycache__/parse.cpython-310.pyc and b/vllm/inputs/__pycache__/parse.cpython-310.pyc differ diff --git a/vllm/inputs/__pycache__/preprocess.cpython-310.pyc b/vllm/inputs/__pycache__/preprocess.cpython-310.pyc index f0ab2016..e20ea00f 100644 Binary files a/vllm/inputs/__pycache__/preprocess.cpython-310.pyc and b/vllm/inputs/__pycache__/preprocess.cpython-310.pyc differ diff --git a/vllm/inputs/__pycache__/registry.cpython-310.pyc b/vllm/inputs/__pycache__/registry.cpython-310.pyc index 8eaef980..8ba84363 100644 Binary files a/vllm/inputs/__pycache__/registry.cpython-310.pyc and b/vllm/inputs/__pycache__/registry.cpython-310.pyc differ diff --git a/vllm/logging/__pycache__/__init__.cpython-310.pyc b/vllm/logging/__pycache__/__init__.cpython-310.pyc index 84691e35..f63a1625 100644 Binary files a/vllm/logging/__pycache__/__init__.cpython-310.pyc and b/vllm/logging/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/logging/__pycache__/formatter.cpython-310.pyc b/vllm/logging/__pycache__/formatter.cpython-310.pyc index ac687a98..06654211 100644 Binary files a/vllm/logging/__pycache__/formatter.cpython-310.pyc and b/vllm/logging/__pycache__/formatter.cpython-310.pyc differ diff --git a/vllm/lora/__pycache__/__init__.cpython-310.pyc b/vllm/lora/__pycache__/__init__.cpython-310.pyc index 6a0040c8..ae16c494 100644 Binary files a/vllm/lora/__pycache__/__init__.cpython-310.pyc and b/vllm/lora/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/lora/__pycache__/request.cpython-310.pyc b/vllm/lora/__pycache__/request.cpython-310.pyc index 0d466eef..39e31433 100644 Binary files a/vllm/lora/__pycache__/request.cpython-310.pyc and b/vllm/lora/__pycache__/request.cpython-310.pyc differ diff --git a/vllm/model_executor/__pycache__/__init__.cpython-310.pyc b/vllm/model_executor/__pycache__/__init__.cpython-310.pyc index 984b8c10..421f74ba 100644 Binary files a/vllm/model_executor/__pycache__/__init__.cpython-310.pyc and b/vllm/model_executor/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/model_executor/__pycache__/custom_op.cpython-310.pyc b/vllm/model_executor/__pycache__/custom_op.cpython-310.pyc index ddaac9a8..f1ba15b2 100644 Binary files a/vllm/model_executor/__pycache__/custom_op.cpython-310.pyc and b/vllm/model_executor/__pycache__/custom_op.cpython-310.pyc differ diff --git a/vllm/model_executor/__pycache__/parameter.cpython-310.pyc b/vllm/model_executor/__pycache__/parameter.cpython-310.pyc index 78a8ef1d..3afe744b 100644 Binary files a/vllm/model_executor/__pycache__/parameter.cpython-310.pyc and b/vllm/model_executor/__pycache__/parameter.cpython-310.pyc differ diff --git a/vllm/model_executor/__pycache__/sampling_metadata.cpython-310.pyc b/vllm/model_executor/__pycache__/sampling_metadata.cpython-310.pyc index d919ff25..eea46e0a 100644 Binary files a/vllm/model_executor/__pycache__/sampling_metadata.cpython-310.pyc and b/vllm/model_executor/__pycache__/sampling_metadata.cpython-310.pyc differ diff --git a/vllm/model_executor/__pycache__/utils.cpython-310.pyc b/vllm/model_executor/__pycache__/utils.cpython-310.pyc index 96650f93..701fc866 100644 Binary files a/vllm/model_executor/__pycache__/utils.cpython-310.pyc and b/vllm/model_executor/__pycache__/utils.cpython-310.pyc differ diff --git a/vllm/model_executor/guided_decoding/__pycache__/__init__.cpython-310.pyc b/vllm/model_executor/guided_decoding/__pycache__/__init__.cpython-310.pyc index 59e35da1..28579317 100644 Binary files a/vllm/model_executor/guided_decoding/__pycache__/__init__.cpython-310.pyc and b/vllm/model_executor/guided_decoding/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/model_executor/guided_decoding/__pycache__/guided_fields.cpython-310.pyc b/vllm/model_executor/guided_decoding/__pycache__/guided_fields.cpython-310.pyc index fbc73927..fba47425 100644 Binary files a/vllm/model_executor/guided_decoding/__pycache__/guided_fields.cpython-310.pyc and b/vllm/model_executor/guided_decoding/__pycache__/guided_fields.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/__pycache__/__init__.cpython-310.pyc b/vllm/model_executor/layers/__pycache__/__init__.cpython-310.pyc index 7d3f1459..81677ab4 100644 Binary files a/vllm/model_executor/layers/__pycache__/__init__.cpython-310.pyc and b/vllm/model_executor/layers/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/__pycache__/linear.cpython-310.pyc b/vllm/model_executor/layers/__pycache__/linear.cpython-310.pyc index c1cc88f6..15218011 100644 Binary files a/vllm/model_executor/layers/__pycache__/linear.cpython-310.pyc and b/vllm/model_executor/layers/__pycache__/linear.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/__pycache__/sampler.cpython-310.pyc b/vllm/model_executor/layers/__pycache__/sampler.cpython-310.pyc index 4fa31a30..141fdd95 100644 Binary files a/vllm/model_executor/layers/__pycache__/sampler.cpython-310.pyc and b/vllm/model_executor/layers/__pycache__/sampler.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/__pycache__/spec_decode_base_sampler.cpython-310.pyc b/vllm/model_executor/layers/__pycache__/spec_decode_base_sampler.cpython-310.pyc index ae776c2d..cc8eeaa7 100644 Binary files a/vllm/model_executor/layers/__pycache__/spec_decode_base_sampler.cpython-310.pyc and b/vllm/model_executor/layers/__pycache__/spec_decode_base_sampler.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/__pycache__/vocab_parallel_embedding.cpython-310.pyc b/vllm/model_executor/layers/__pycache__/vocab_parallel_embedding.cpython-310.pyc index 321681b2..1f147956 100644 Binary files a/vllm/model_executor/layers/__pycache__/vocab_parallel_embedding.cpython-310.pyc and b/vllm/model_executor/layers/__pycache__/vocab_parallel_embedding.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/fused_moe/__pycache__/__init__.cpython-310.pyc b/vllm/model_executor/layers/fused_moe/__pycache__/__init__.cpython-310.pyc index 2b6e09f7..c2533055 100644 Binary files a/vllm/model_executor/layers/fused_moe/__pycache__/__init__.cpython-310.pyc and b/vllm/model_executor/layers/fused_moe/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/fused_moe/__pycache__/fused_marlin_moe.cpython-310.pyc b/vllm/model_executor/layers/fused_moe/__pycache__/fused_marlin_moe.cpython-310.pyc index e8c7e522..d6a81e1f 100644 Binary files a/vllm/model_executor/layers/fused_moe/__pycache__/fused_marlin_moe.cpython-310.pyc and b/vllm/model_executor/layers/fused_moe/__pycache__/fused_marlin_moe.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/fused_moe/__pycache__/fused_moe.cpython-310.pyc b/vllm/model_executor/layers/fused_moe/__pycache__/fused_moe.cpython-310.pyc index 0fd89596..a8998d5e 100644 Binary files a/vllm/model_executor/layers/fused_moe/__pycache__/fused_moe.cpython-310.pyc and b/vllm/model_executor/layers/fused_moe/__pycache__/fused_moe.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/fused_moe/__pycache__/layer.cpython-310.pyc b/vllm/model_executor/layers/fused_moe/__pycache__/layer.cpython-310.pyc index 9684cff7..ac60ed22 100644 Binary files a/vllm/model_executor/layers/fused_moe/__pycache__/layer.cpython-310.pyc and b/vllm/model_executor/layers/fused_moe/__pycache__/layer.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/__pycache__/__init__.cpython-310.pyc b/vllm/model_executor/layers/quantization/__pycache__/__init__.cpython-310.pyc index c2312d92..604ce81c 100644 Binary files a/vllm/model_executor/layers/quantization/__pycache__/__init__.cpython-310.pyc and b/vllm/model_executor/layers/quantization/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/__pycache__/aqlm.cpython-310.pyc b/vllm/model_executor/layers/quantization/__pycache__/aqlm.cpython-310.pyc index 97c6107c..b6411a0c 100644 Binary files a/vllm/model_executor/layers/quantization/__pycache__/aqlm.cpython-310.pyc and b/vllm/model_executor/layers/quantization/__pycache__/aqlm.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/__pycache__/awq.cpython-310.pyc b/vllm/model_executor/layers/quantization/__pycache__/awq.cpython-310.pyc index 33b34e6a..b4313583 100644 Binary files a/vllm/model_executor/layers/quantization/__pycache__/awq.cpython-310.pyc and b/vllm/model_executor/layers/quantization/__pycache__/awq.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/__pycache__/awq_marlin.cpython-310.pyc b/vllm/model_executor/layers/quantization/__pycache__/awq_marlin.cpython-310.pyc index bccc8e3f..da2226f6 100644 Binary files a/vllm/model_executor/layers/quantization/__pycache__/awq_marlin.cpython-310.pyc and b/vllm/model_executor/layers/quantization/__pycache__/awq_marlin.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/__pycache__/base_config.cpython-310.pyc b/vllm/model_executor/layers/quantization/__pycache__/base_config.cpython-310.pyc index 39e0f44b..9854775d 100644 Binary files a/vllm/model_executor/layers/quantization/__pycache__/base_config.cpython-310.pyc and b/vllm/model_executor/layers/quantization/__pycache__/base_config.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/__pycache__/bitsandbytes.cpython-310.pyc b/vllm/model_executor/layers/quantization/__pycache__/bitsandbytes.cpython-310.pyc index 5e8362e3..8d82027c 100644 Binary files a/vllm/model_executor/layers/quantization/__pycache__/bitsandbytes.cpython-310.pyc and b/vllm/model_executor/layers/quantization/__pycache__/bitsandbytes.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/__pycache__/deepspeedfp.cpython-310.pyc b/vllm/model_executor/layers/quantization/__pycache__/deepspeedfp.cpython-310.pyc index a31daaab..63e85074 100644 Binary files a/vllm/model_executor/layers/quantization/__pycache__/deepspeedfp.cpython-310.pyc and b/vllm/model_executor/layers/quantization/__pycache__/deepspeedfp.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/__pycache__/experts_int8.cpython-310.pyc b/vllm/model_executor/layers/quantization/__pycache__/experts_int8.cpython-310.pyc index 8957b279..8b21597b 100644 Binary files a/vllm/model_executor/layers/quantization/__pycache__/experts_int8.cpython-310.pyc and b/vllm/model_executor/layers/quantization/__pycache__/experts_int8.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/__pycache__/fbgemm_fp8.cpython-310.pyc b/vllm/model_executor/layers/quantization/__pycache__/fbgemm_fp8.cpython-310.pyc index 54b49c92..653faed6 100644 Binary files a/vllm/model_executor/layers/quantization/__pycache__/fbgemm_fp8.cpython-310.pyc and b/vllm/model_executor/layers/quantization/__pycache__/fbgemm_fp8.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/__pycache__/fp8.cpython-310.pyc b/vllm/model_executor/layers/quantization/__pycache__/fp8.cpython-310.pyc index 69d150f8..69307e97 100644 Binary files a/vllm/model_executor/layers/quantization/__pycache__/fp8.cpython-310.pyc and b/vllm/model_executor/layers/quantization/__pycache__/fp8.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/__pycache__/gguf.cpython-310.pyc b/vllm/model_executor/layers/quantization/__pycache__/gguf.cpython-310.pyc index 72e41dae..83bba2de 100644 Binary files a/vllm/model_executor/layers/quantization/__pycache__/gguf.cpython-310.pyc and b/vllm/model_executor/layers/quantization/__pycache__/gguf.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/__pycache__/gptq.cpython-310.pyc b/vllm/model_executor/layers/quantization/__pycache__/gptq.cpython-310.pyc index a9d75f12..4d3e1aee 100644 Binary files a/vllm/model_executor/layers/quantization/__pycache__/gptq.cpython-310.pyc and b/vllm/model_executor/layers/quantization/__pycache__/gptq.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/__pycache__/gptq_marlin.cpython-310.pyc b/vllm/model_executor/layers/quantization/__pycache__/gptq_marlin.cpython-310.pyc index d54eeef2..37db2758 100644 Binary files a/vllm/model_executor/layers/quantization/__pycache__/gptq_marlin.cpython-310.pyc and b/vllm/model_executor/layers/quantization/__pycache__/gptq_marlin.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/__pycache__/gptq_marlin_24.cpython-310.pyc b/vllm/model_executor/layers/quantization/__pycache__/gptq_marlin_24.cpython-310.pyc index fbc58d26..b8ca4212 100644 Binary files a/vllm/model_executor/layers/quantization/__pycache__/gptq_marlin_24.cpython-310.pyc and b/vllm/model_executor/layers/quantization/__pycache__/gptq_marlin_24.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/__pycache__/ipex_quant.cpython-310.pyc b/vllm/model_executor/layers/quantization/__pycache__/ipex_quant.cpython-310.pyc index 4b11c2f2..e54fd25c 100644 Binary files a/vllm/model_executor/layers/quantization/__pycache__/ipex_quant.cpython-310.pyc and b/vllm/model_executor/layers/quantization/__pycache__/ipex_quant.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/__pycache__/kv_cache.cpython-310.pyc b/vllm/model_executor/layers/quantization/__pycache__/kv_cache.cpython-310.pyc index 44e5b410..b480070b 100644 Binary files a/vllm/model_executor/layers/quantization/__pycache__/kv_cache.cpython-310.pyc and b/vllm/model_executor/layers/quantization/__pycache__/kv_cache.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/__pycache__/marlin.cpython-310.pyc b/vllm/model_executor/layers/quantization/__pycache__/marlin.cpython-310.pyc index 5f1f5fc0..366a68e9 100644 Binary files a/vllm/model_executor/layers/quantization/__pycache__/marlin.cpython-310.pyc and b/vllm/model_executor/layers/quantization/__pycache__/marlin.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/__pycache__/modelopt.cpython-310.pyc b/vllm/model_executor/layers/quantization/__pycache__/modelopt.cpython-310.pyc index 87d5593a..e183ab23 100644 Binary files a/vllm/model_executor/layers/quantization/__pycache__/modelopt.cpython-310.pyc and b/vllm/model_executor/layers/quantization/__pycache__/modelopt.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/__pycache__/neuron_quant.cpython-310.pyc b/vllm/model_executor/layers/quantization/__pycache__/neuron_quant.cpython-310.pyc index 540c07b9..b2502a4f 100644 Binary files a/vllm/model_executor/layers/quantization/__pycache__/neuron_quant.cpython-310.pyc and b/vllm/model_executor/layers/quantization/__pycache__/neuron_quant.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/__pycache__/qqq.cpython-310.pyc b/vllm/model_executor/layers/quantization/__pycache__/qqq.cpython-310.pyc index 32780cf8..4f52f555 100644 Binary files a/vllm/model_executor/layers/quantization/__pycache__/qqq.cpython-310.pyc and b/vllm/model_executor/layers/quantization/__pycache__/qqq.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/__pycache__/tpu_int8.cpython-310.pyc b/vllm/model_executor/layers/quantization/__pycache__/tpu_int8.cpython-310.pyc index 470be320..b845e7cf 100644 Binary files a/vllm/model_executor/layers/quantization/__pycache__/tpu_int8.cpython-310.pyc and b/vllm/model_executor/layers/quantization/__pycache__/tpu_int8.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/__pycache__/w8a16.cpython-310.pyc b/vllm/model_executor/layers/quantization/__pycache__/w8a16.cpython-310.pyc index 9a134f3a..6233d9f2 100644 Binary files a/vllm/model_executor/layers/quantization/__pycache__/w8a16.cpython-310.pyc and b/vllm/model_executor/layers/quantization/__pycache__/w8a16.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/compressed_tensors/__pycache__/__init__.cpython-310.pyc b/vllm/model_executor/layers/quantization/compressed_tensors/__pycache__/__init__.cpython-310.pyc index a5510838..68eeae05 100644 Binary files a/vllm/model_executor/layers/quantization/compressed_tensors/__pycache__/__init__.cpython-310.pyc and b/vllm/model_executor/layers/quantization/compressed_tensors/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/compressed_tensors/__pycache__/compressed_tensors.cpython-310.pyc b/vllm/model_executor/layers/quantization/compressed_tensors/__pycache__/compressed_tensors.cpython-310.pyc index db6f166e..974a023f 100644 Binary files a/vllm/model_executor/layers/quantization/compressed_tensors/__pycache__/compressed_tensors.cpython-310.pyc and b/vllm/model_executor/layers/quantization/compressed_tensors/__pycache__/compressed_tensors.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/compressed_tensors/__pycache__/compressed_tensors_moe.cpython-310.pyc b/vllm/model_executor/layers/quantization/compressed_tensors/__pycache__/compressed_tensors_moe.cpython-310.pyc index c2bceb07..ec089a8a 100644 Binary files a/vllm/model_executor/layers/quantization/compressed_tensors/__pycache__/compressed_tensors_moe.cpython-310.pyc and b/vllm/model_executor/layers/quantization/compressed_tensors/__pycache__/compressed_tensors_moe.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/compressed_tensors/__pycache__/utils.cpython-310.pyc b/vllm/model_executor/layers/quantization/compressed_tensors/__pycache__/utils.cpython-310.pyc index 408ed020..e3f672d9 100644 Binary files a/vllm/model_executor/layers/quantization/compressed_tensors/__pycache__/utils.cpython-310.pyc and b/vllm/model_executor/layers/quantization/compressed_tensors/__pycache__/utils.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__pycache__/__init__.cpython-310.pyc b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__pycache__/__init__.cpython-310.pyc index d24a3fc0..feb5095b 100644 Binary files a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__pycache__/__init__.cpython-310.pyc and b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__pycache__/compressed_tensors_scheme.cpython-310.pyc b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__pycache__/compressed_tensors_scheme.cpython-310.pyc index fe4692ab..da1f1f6a 100644 Binary files a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__pycache__/compressed_tensors_scheme.cpython-310.pyc and b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__pycache__/compressed_tensors_scheme.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__pycache__/compressed_tensors_w4a16_24.cpython-310.pyc b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__pycache__/compressed_tensors_w4a16_24.cpython-310.pyc index 258d5040..ff3e1306 100644 Binary files a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__pycache__/compressed_tensors_w4a16_24.cpython-310.pyc and b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__pycache__/compressed_tensors_w4a16_24.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__pycache__/compressed_tensors_w8a16_fp8.cpython-310.pyc b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__pycache__/compressed_tensors_w8a16_fp8.cpython-310.pyc index a286914b..876114d9 100644 Binary files a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__pycache__/compressed_tensors_w8a16_fp8.cpython-310.pyc and b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__pycache__/compressed_tensors_w8a16_fp8.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__pycache__/compressed_tensors_w8a8_fp8.cpython-310.pyc b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__pycache__/compressed_tensors_w8a8_fp8.cpython-310.pyc index 9d03344a..24033fb8 100644 Binary files a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__pycache__/compressed_tensors_w8a8_fp8.cpython-310.pyc and b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__pycache__/compressed_tensors_w8a8_fp8.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__pycache__/compressed_tensors_w8a8_int8.cpython-310.pyc b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__pycache__/compressed_tensors_w8a8_int8.cpython-310.pyc index f2aa37c8..885529e9 100644 Binary files a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__pycache__/compressed_tensors_w8a8_int8.cpython-310.pyc and b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__pycache__/compressed_tensors_w8a8_int8.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__pycache__/compressed_tensors_wNa16.cpython-310.pyc b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__pycache__/compressed_tensors_wNa16.cpython-310.pyc index c84fb933..28ca66a9 100644 Binary files a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__pycache__/compressed_tensors_wNa16.cpython-310.pyc and b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__pycache__/compressed_tensors_wNa16.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/kernels/__pycache__/MPLinearKernel.cpython-310.pyc b/vllm/model_executor/layers/quantization/kernels/__pycache__/MPLinearKernel.cpython-310.pyc index 6690d8b2..3f44c3b2 100644 Binary files a/vllm/model_executor/layers/quantization/kernels/__pycache__/MPLinearKernel.cpython-310.pyc and b/vllm/model_executor/layers/quantization/kernels/__pycache__/MPLinearKernel.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/kernels/__pycache__/__init__.cpython-310.pyc b/vllm/model_executor/layers/quantization/kernels/__pycache__/__init__.cpython-310.pyc index f2827fc5..80266963 100644 Binary files a/vllm/model_executor/layers/quantization/kernels/__pycache__/__init__.cpython-310.pyc and b/vllm/model_executor/layers/quantization/kernels/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/kernels/__pycache__/machete.cpython-310.pyc b/vllm/model_executor/layers/quantization/kernels/__pycache__/machete.cpython-310.pyc index 6c0760b8..1e75a511 100644 Binary files a/vllm/model_executor/layers/quantization/kernels/__pycache__/machete.cpython-310.pyc and b/vllm/model_executor/layers/quantization/kernels/__pycache__/machete.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/kernels/__pycache__/marlin.cpython-310.pyc b/vllm/model_executor/layers/quantization/kernels/__pycache__/marlin.cpython-310.pyc index b226a8ec..6bd299a6 100644 Binary files a/vllm/model_executor/layers/quantization/kernels/__pycache__/marlin.cpython-310.pyc and b/vllm/model_executor/layers/quantization/kernels/__pycache__/marlin.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/utils/__pycache__/__init__.cpython-310.pyc b/vllm/model_executor/layers/quantization/utils/__pycache__/__init__.cpython-310.pyc index ea126a2b..d20c04eb 100644 Binary files a/vllm/model_executor/layers/quantization/utils/__pycache__/__init__.cpython-310.pyc and b/vllm/model_executor/layers/quantization/utils/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/utils/__pycache__/layer_utils.cpython-310.pyc b/vllm/model_executor/layers/quantization/utils/__pycache__/layer_utils.cpython-310.pyc index 7a710e9d..0b475440 100644 Binary files a/vllm/model_executor/layers/quantization/utils/__pycache__/layer_utils.cpython-310.pyc and b/vllm/model_executor/layers/quantization/utils/__pycache__/layer_utils.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/utils/__pycache__/machete_utils.cpython-310.pyc b/vllm/model_executor/layers/quantization/utils/__pycache__/machete_utils.cpython-310.pyc index 1d236964..3b1015fc 100644 Binary files a/vllm/model_executor/layers/quantization/utils/__pycache__/machete_utils.cpython-310.pyc and b/vllm/model_executor/layers/quantization/utils/__pycache__/machete_utils.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/utils/__pycache__/marlin_utils.cpython-310.pyc b/vllm/model_executor/layers/quantization/utils/__pycache__/marlin_utils.cpython-310.pyc index 8c4e2f53..1d09eb9d 100644 Binary files a/vllm/model_executor/layers/quantization/utils/__pycache__/marlin_utils.cpython-310.pyc and b/vllm/model_executor/layers/quantization/utils/__pycache__/marlin_utils.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/utils/__pycache__/marlin_utils_fp8.cpython-310.pyc b/vllm/model_executor/layers/quantization/utils/__pycache__/marlin_utils_fp8.cpython-310.pyc index fbd93ab7..318e84b0 100644 Binary files a/vllm/model_executor/layers/quantization/utils/__pycache__/marlin_utils_fp8.cpython-310.pyc and b/vllm/model_executor/layers/quantization/utils/__pycache__/marlin_utils_fp8.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/utils/__pycache__/quant_utils.cpython-310.pyc b/vllm/model_executor/layers/quantization/utils/__pycache__/quant_utils.cpython-310.pyc index 53790651..e9877647 100644 Binary files a/vllm/model_executor/layers/quantization/utils/__pycache__/quant_utils.cpython-310.pyc and b/vllm/model_executor/layers/quantization/utils/__pycache__/quant_utils.cpython-310.pyc differ diff --git a/vllm/model_executor/layers/quantization/utils/__pycache__/w8a8_utils.cpython-310.pyc b/vllm/model_executor/layers/quantization/utils/__pycache__/w8a8_utils.cpython-310.pyc index e32cfbfe..030d2f76 100644 Binary files a/vllm/model_executor/layers/quantization/utils/__pycache__/w8a8_utils.cpython-310.pyc and b/vllm/model_executor/layers/quantization/utils/__pycache__/w8a8_utils.cpython-310.pyc differ diff --git a/vllm/model_executor/models/__pycache__/__init__.cpython-310.pyc b/vllm/model_executor/models/__pycache__/__init__.cpython-310.pyc index d17d8c80..769bbc9a 100644 Binary files a/vllm/model_executor/models/__pycache__/__init__.cpython-310.pyc and b/vllm/model_executor/models/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/model_executor/models/__pycache__/interfaces.cpython-310.pyc b/vllm/model_executor/models/__pycache__/interfaces.cpython-310.pyc index 54a8e4bb..8deb891d 100644 Binary files a/vllm/model_executor/models/__pycache__/interfaces.cpython-310.pyc and b/vllm/model_executor/models/__pycache__/interfaces.cpython-310.pyc differ diff --git a/vllm/model_executor/models/__pycache__/interfaces_base.cpython-310.pyc b/vllm/model_executor/models/__pycache__/interfaces_base.cpython-310.pyc index 30730cf6..1fe8c756 100644 Binary files a/vllm/model_executor/models/__pycache__/interfaces_base.cpython-310.pyc and b/vllm/model_executor/models/__pycache__/interfaces_base.cpython-310.pyc differ diff --git a/vllm/model_executor/models/__pycache__/registry.cpython-310.pyc b/vllm/model_executor/models/__pycache__/registry.cpython-310.pyc index 576a5383..b3fbeabb 100644 Binary files a/vllm/model_executor/models/__pycache__/registry.cpython-310.pyc and b/vllm/model_executor/models/__pycache__/registry.cpython-310.pyc differ diff --git a/vllm/multimodal/__pycache__/__init__.cpython-310.pyc b/vllm/multimodal/__pycache__/__init__.cpython-310.pyc index ab4b7072..089856cb 100644 Binary files a/vllm/multimodal/__pycache__/__init__.cpython-310.pyc and b/vllm/multimodal/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/multimodal/__pycache__/audio.cpython-310.pyc b/vllm/multimodal/__pycache__/audio.cpython-310.pyc index a1bbd41d..d79a0d9d 100644 Binary files a/vllm/multimodal/__pycache__/audio.cpython-310.pyc and b/vllm/multimodal/__pycache__/audio.cpython-310.pyc differ diff --git a/vllm/multimodal/__pycache__/base.cpython-310.pyc b/vllm/multimodal/__pycache__/base.cpython-310.pyc index b2ae8478..eea342e0 100644 Binary files a/vllm/multimodal/__pycache__/base.cpython-310.pyc and b/vllm/multimodal/__pycache__/base.cpython-310.pyc differ diff --git a/vllm/multimodal/__pycache__/image.cpython-310.pyc b/vllm/multimodal/__pycache__/image.cpython-310.pyc index d5898d2a..783b8f9d 100644 Binary files a/vllm/multimodal/__pycache__/image.cpython-310.pyc and b/vllm/multimodal/__pycache__/image.cpython-310.pyc differ diff --git a/vllm/multimodal/__pycache__/registry.cpython-310.pyc b/vllm/multimodal/__pycache__/registry.cpython-310.pyc index 350ec502..55f72081 100644 Binary files a/vllm/multimodal/__pycache__/registry.cpython-310.pyc and b/vllm/multimodal/__pycache__/registry.cpython-310.pyc differ diff --git a/vllm/multimodal/__pycache__/utils.cpython-310.pyc b/vllm/multimodal/__pycache__/utils.cpython-310.pyc index d04d3df1..72b3f2fa 100644 Binary files a/vllm/multimodal/__pycache__/utils.cpython-310.pyc and b/vllm/multimodal/__pycache__/utils.cpython-310.pyc differ diff --git a/vllm/multimodal/__pycache__/video.cpython-310.pyc b/vllm/multimodal/__pycache__/video.cpython-310.pyc index e2d31636..a17d8c99 100644 Binary files a/vllm/multimodal/__pycache__/video.cpython-310.pyc and b/vllm/multimodal/__pycache__/video.cpython-310.pyc differ diff --git a/vllm/platforms/__pycache__/__init__.cpython-310.pyc b/vllm/platforms/__pycache__/__init__.cpython-310.pyc index 0b50dc41..10171bc3 100644 Binary files a/vllm/platforms/__pycache__/__init__.cpython-310.pyc and b/vllm/platforms/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/platforms/__pycache__/cuda.cpython-310.pyc b/vllm/platforms/__pycache__/cuda.cpython-310.pyc index 6c4935a6..4683263a 100644 Binary files a/vllm/platforms/__pycache__/cuda.cpython-310.pyc and b/vllm/platforms/__pycache__/cuda.cpython-310.pyc differ diff --git a/vllm/platforms/__pycache__/interface.cpython-310.pyc b/vllm/platforms/__pycache__/interface.cpython-310.pyc index 053ec4f9..e565d225 100644 Binary files a/vllm/platforms/__pycache__/interface.cpython-310.pyc and b/vllm/platforms/__pycache__/interface.cpython-310.pyc differ diff --git a/vllm/prompt_adapter/__pycache__/__init__.cpython-310.pyc b/vllm/prompt_adapter/__pycache__/__init__.cpython-310.pyc index a0d7d61e..4e5c16e1 100644 Binary files a/vllm/prompt_adapter/__pycache__/__init__.cpython-310.pyc and b/vllm/prompt_adapter/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/prompt_adapter/__pycache__/request.cpython-310.pyc b/vllm/prompt_adapter/__pycache__/request.cpython-310.pyc index 29f2651f..ec7127bb 100644 Binary files a/vllm/prompt_adapter/__pycache__/request.cpython-310.pyc and b/vllm/prompt_adapter/__pycache__/request.cpython-310.pyc differ diff --git a/vllm/spec_decode/__pycache__/__init__.cpython-310.pyc b/vllm/spec_decode/__pycache__/__init__.cpython-310.pyc index bccb28a1..159e033a 100644 Binary files a/vllm/spec_decode/__pycache__/__init__.cpython-310.pyc and b/vllm/spec_decode/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/spec_decode/__pycache__/metrics.cpython-310.pyc b/vllm/spec_decode/__pycache__/metrics.cpython-310.pyc index 9518ee31..3c8da958 100644 Binary files a/vllm/spec_decode/__pycache__/metrics.cpython-310.pyc and b/vllm/spec_decode/__pycache__/metrics.cpython-310.pyc differ diff --git a/vllm/transformers_utils/__pycache__/__init__.cpython-310.pyc b/vllm/transformers_utils/__pycache__/__init__.cpython-310.pyc index 628a03dc..7674c45d 100644 Binary files a/vllm/transformers_utils/__pycache__/__init__.cpython-310.pyc and b/vllm/transformers_utils/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/transformers_utils/__pycache__/config.cpython-310.pyc b/vllm/transformers_utils/__pycache__/config.cpython-310.pyc index 532911cc..d9f953b6 100644 Binary files a/vllm/transformers_utils/__pycache__/config.cpython-310.pyc and b/vllm/transformers_utils/__pycache__/config.cpython-310.pyc differ diff --git a/vllm/transformers_utils/__pycache__/detokenizer.cpython-310.pyc b/vllm/transformers_utils/__pycache__/detokenizer.cpython-310.pyc index 6812464a..810e894b 100644 Binary files a/vllm/transformers_utils/__pycache__/detokenizer.cpython-310.pyc and b/vllm/transformers_utils/__pycache__/detokenizer.cpython-310.pyc differ diff --git a/vllm/transformers_utils/__pycache__/processor.cpython-310.pyc b/vllm/transformers_utils/__pycache__/processor.cpython-310.pyc index 92197bef..73bb176b 100644 Binary files a/vllm/transformers_utils/__pycache__/processor.cpython-310.pyc and b/vllm/transformers_utils/__pycache__/processor.cpython-310.pyc differ diff --git a/vllm/transformers_utils/__pycache__/tokenizer.cpython-310.pyc b/vllm/transformers_utils/__pycache__/tokenizer.cpython-310.pyc index 191d2845..bfdc9459 100644 Binary files a/vllm/transformers_utils/__pycache__/tokenizer.cpython-310.pyc and b/vllm/transformers_utils/__pycache__/tokenizer.cpython-310.pyc differ diff --git a/vllm/transformers_utils/__pycache__/utils.cpython-310.pyc b/vllm/transformers_utils/__pycache__/utils.cpython-310.pyc index 4dc959c4..320378c6 100644 Binary files a/vllm/transformers_utils/__pycache__/utils.cpython-310.pyc and b/vllm/transformers_utils/__pycache__/utils.cpython-310.pyc differ diff --git a/vllm/transformers_utils/configs/__pycache__/__init__.cpython-310.pyc b/vllm/transformers_utils/configs/__pycache__/__init__.cpython-310.pyc index 52a9ae47..7122cffb 100644 Binary files a/vllm/transformers_utils/configs/__pycache__/__init__.cpython-310.pyc and b/vllm/transformers_utils/configs/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/transformers_utils/configs/__pycache__/chatglm.cpython-310.pyc b/vllm/transformers_utils/configs/__pycache__/chatglm.cpython-310.pyc index b8baa1b9..5c8a92f5 100644 Binary files a/vllm/transformers_utils/configs/__pycache__/chatglm.cpython-310.pyc and b/vllm/transformers_utils/configs/__pycache__/chatglm.cpython-310.pyc differ diff --git a/vllm/transformers_utils/configs/__pycache__/dbrx.cpython-310.pyc b/vllm/transformers_utils/configs/__pycache__/dbrx.cpython-310.pyc index f014576a..4ce22c88 100644 Binary files a/vllm/transformers_utils/configs/__pycache__/dbrx.cpython-310.pyc and b/vllm/transformers_utils/configs/__pycache__/dbrx.cpython-310.pyc differ diff --git a/vllm/transformers_utils/configs/__pycache__/eagle.cpython-310.pyc b/vllm/transformers_utils/configs/__pycache__/eagle.cpython-310.pyc index be8b08a2..30e70ef8 100644 Binary files a/vllm/transformers_utils/configs/__pycache__/eagle.cpython-310.pyc and b/vllm/transformers_utils/configs/__pycache__/eagle.cpython-310.pyc differ diff --git a/vllm/transformers_utils/configs/__pycache__/exaone.cpython-310.pyc b/vllm/transformers_utils/configs/__pycache__/exaone.cpython-310.pyc index c39474db..e0094416 100644 Binary files a/vllm/transformers_utils/configs/__pycache__/exaone.cpython-310.pyc and b/vllm/transformers_utils/configs/__pycache__/exaone.cpython-310.pyc differ diff --git a/vllm/transformers_utils/configs/__pycache__/falcon.cpython-310.pyc b/vllm/transformers_utils/configs/__pycache__/falcon.cpython-310.pyc index 49f16255..f65587dd 100644 Binary files a/vllm/transformers_utils/configs/__pycache__/falcon.cpython-310.pyc and b/vllm/transformers_utils/configs/__pycache__/falcon.cpython-310.pyc differ diff --git a/vllm/transformers_utils/configs/__pycache__/internvl.cpython-310.pyc b/vllm/transformers_utils/configs/__pycache__/internvl.cpython-310.pyc index 84778903..1a105942 100644 Binary files a/vllm/transformers_utils/configs/__pycache__/internvl.cpython-310.pyc and b/vllm/transformers_utils/configs/__pycache__/internvl.cpython-310.pyc differ diff --git a/vllm/transformers_utils/configs/__pycache__/jais.cpython-310.pyc b/vllm/transformers_utils/configs/__pycache__/jais.cpython-310.pyc index 777501a4..3d3ede1e 100644 Binary files a/vllm/transformers_utils/configs/__pycache__/jais.cpython-310.pyc and b/vllm/transformers_utils/configs/__pycache__/jais.cpython-310.pyc differ diff --git a/vllm/transformers_utils/configs/__pycache__/medusa.cpython-310.pyc b/vllm/transformers_utils/configs/__pycache__/medusa.cpython-310.pyc index ad40fe5b..5e6704b4 100644 Binary files a/vllm/transformers_utils/configs/__pycache__/medusa.cpython-310.pyc and b/vllm/transformers_utils/configs/__pycache__/medusa.cpython-310.pyc differ diff --git a/vllm/transformers_utils/configs/__pycache__/mllama.cpython-310.pyc b/vllm/transformers_utils/configs/__pycache__/mllama.cpython-310.pyc index e2470257..02be2109 100644 Binary files a/vllm/transformers_utils/configs/__pycache__/mllama.cpython-310.pyc and b/vllm/transformers_utils/configs/__pycache__/mllama.cpython-310.pyc differ diff --git a/vllm/transformers_utils/configs/__pycache__/mlp_speculator.cpython-310.pyc b/vllm/transformers_utils/configs/__pycache__/mlp_speculator.cpython-310.pyc index 8ce7a6d5..308c5322 100644 Binary files a/vllm/transformers_utils/configs/__pycache__/mlp_speculator.cpython-310.pyc and b/vllm/transformers_utils/configs/__pycache__/mlp_speculator.cpython-310.pyc differ diff --git a/vllm/transformers_utils/configs/__pycache__/mpt.cpython-310.pyc b/vllm/transformers_utils/configs/__pycache__/mpt.cpython-310.pyc index 07ea9347..82999881 100644 Binary files a/vllm/transformers_utils/configs/__pycache__/mpt.cpython-310.pyc and b/vllm/transformers_utils/configs/__pycache__/mpt.cpython-310.pyc differ diff --git a/vllm/transformers_utils/configs/__pycache__/nemotron.cpython-310.pyc b/vllm/transformers_utils/configs/__pycache__/nemotron.cpython-310.pyc index 693b3ca2..bf15afac 100644 Binary files a/vllm/transformers_utils/configs/__pycache__/nemotron.cpython-310.pyc and b/vllm/transformers_utils/configs/__pycache__/nemotron.cpython-310.pyc differ diff --git a/vllm/transformers_utils/configs/__pycache__/nvlm_d.cpython-310.pyc b/vllm/transformers_utils/configs/__pycache__/nvlm_d.cpython-310.pyc index f9cee42c..aa5de81a 100644 Binary files a/vllm/transformers_utils/configs/__pycache__/nvlm_d.cpython-310.pyc and b/vllm/transformers_utils/configs/__pycache__/nvlm_d.cpython-310.pyc differ diff --git a/vllm/transformers_utils/configs/__pycache__/qwen2vl.cpython-310.pyc b/vllm/transformers_utils/configs/__pycache__/qwen2vl.cpython-310.pyc index 32491a11..c7e05899 100644 Binary files a/vllm/transformers_utils/configs/__pycache__/qwen2vl.cpython-310.pyc and b/vllm/transformers_utils/configs/__pycache__/qwen2vl.cpython-310.pyc differ diff --git a/vllm/transformers_utils/configs/__pycache__/solar.cpython-310.pyc b/vllm/transformers_utils/configs/__pycache__/solar.cpython-310.pyc index 17a155c1..745845cd 100644 Binary files a/vllm/transformers_utils/configs/__pycache__/solar.cpython-310.pyc and b/vllm/transformers_utils/configs/__pycache__/solar.cpython-310.pyc differ diff --git a/vllm/transformers_utils/configs/__pycache__/ultravox.cpython-310.pyc b/vllm/transformers_utils/configs/__pycache__/ultravox.cpython-310.pyc index 103564d0..3f947d8b 100644 Binary files a/vllm/transformers_utils/configs/__pycache__/ultravox.cpython-310.pyc and b/vllm/transformers_utils/configs/__pycache__/ultravox.cpython-310.pyc differ diff --git a/vllm/transformers_utils/tokenizer_group/__pycache__/__init__.cpython-310.pyc b/vllm/transformers_utils/tokenizer_group/__pycache__/__init__.cpython-310.pyc index f7ff6e46..6bb373b7 100644 Binary files a/vllm/transformers_utils/tokenizer_group/__pycache__/__init__.cpython-310.pyc and b/vllm/transformers_utils/tokenizer_group/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/transformers_utils/tokenizer_group/__pycache__/base_tokenizer_group.cpython-310.pyc b/vllm/transformers_utils/tokenizer_group/__pycache__/base_tokenizer_group.cpython-310.pyc index e1077282..c971c2ad 100644 Binary files a/vllm/transformers_utils/tokenizer_group/__pycache__/base_tokenizer_group.cpython-310.pyc and b/vllm/transformers_utils/tokenizer_group/__pycache__/base_tokenizer_group.cpython-310.pyc differ diff --git a/vllm/transformers_utils/tokenizer_group/__pycache__/ray_tokenizer_group.cpython-310.pyc b/vllm/transformers_utils/tokenizer_group/__pycache__/ray_tokenizer_group.cpython-310.pyc index 5c3bbcc5..51dd154a 100644 Binary files a/vllm/transformers_utils/tokenizer_group/__pycache__/ray_tokenizer_group.cpython-310.pyc and b/vllm/transformers_utils/tokenizer_group/__pycache__/ray_tokenizer_group.cpython-310.pyc differ diff --git a/vllm/transformers_utils/tokenizer_group/__pycache__/tokenizer_group.cpython-310.pyc b/vllm/transformers_utils/tokenizer_group/__pycache__/tokenizer_group.cpython-310.pyc index 0d35ced6..dbd57dfd 100644 Binary files a/vllm/transformers_utils/tokenizer_group/__pycache__/tokenizer_group.cpython-310.pyc and b/vllm/transformers_utils/tokenizer_group/__pycache__/tokenizer_group.cpython-310.pyc differ diff --git a/vllm/transformers_utils/tokenizers/__pycache__/__init__.cpython-310.pyc b/vllm/transformers_utils/tokenizers/__pycache__/__init__.cpython-310.pyc index 1e6b3a2c..f982b750 100644 Binary files a/vllm/transformers_utils/tokenizers/__pycache__/__init__.cpython-310.pyc and b/vllm/transformers_utils/tokenizers/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/transformers_utils/tokenizers/__pycache__/mistral.cpython-310.pyc b/vllm/transformers_utils/tokenizers/__pycache__/mistral.cpython-310.pyc index c3399cc7..4bb8db0b 100644 Binary files a/vllm/transformers_utils/tokenizers/__pycache__/mistral.cpython-310.pyc and b/vllm/transformers_utils/tokenizers/__pycache__/mistral.cpython-310.pyc differ diff --git a/vllm/triton_utils/__pycache__/__init__.cpython-310.pyc b/vllm/triton_utils/__pycache__/__init__.cpython-310.pyc index 1ddb7112..fefb9fc5 100644 Binary files a/vllm/triton_utils/__pycache__/__init__.cpython-310.pyc and b/vllm/triton_utils/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/triton_utils/__pycache__/custom_cache_manager.cpython-310.pyc b/vllm/triton_utils/__pycache__/custom_cache_manager.cpython-310.pyc index 6359ac79..c454404c 100644 Binary files a/vllm/triton_utils/__pycache__/custom_cache_manager.cpython-310.pyc and b/vllm/triton_utils/__pycache__/custom_cache_manager.cpython-310.pyc differ diff --git a/vllm/triton_utils/__pycache__/importing.cpython-310.pyc b/vllm/triton_utils/__pycache__/importing.cpython-310.pyc index 1a189385..973d92bd 100644 Binary files a/vllm/triton_utils/__pycache__/importing.cpython-310.pyc and b/vllm/triton_utils/__pycache__/importing.cpython-310.pyc differ diff --git a/vllm/triton_utils/__pycache__/libentry.cpython-310.pyc b/vllm/triton_utils/__pycache__/libentry.cpython-310.pyc index 2aa05a16..21eac37d 100644 Binary files a/vllm/triton_utils/__pycache__/libentry.cpython-310.pyc and b/vllm/triton_utils/__pycache__/libentry.cpython-310.pyc differ diff --git a/vllm/usage/__pycache__/__init__.cpython-310.pyc b/vllm/usage/__pycache__/__init__.cpython-310.pyc index 2ebb6633..feab1898 100644 Binary files a/vllm/usage/__pycache__/__init__.cpython-310.pyc and b/vllm/usage/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/usage/__pycache__/usage_lib.cpython-310.pyc b/vllm/usage/__pycache__/usage_lib.cpython-310.pyc index b7990bfe..e02b0d7a 100644 Binary files a/vllm/usage/__pycache__/usage_lib.cpython-310.pyc and b/vllm/usage/__pycache__/usage_lib.cpython-310.pyc differ diff --git a/vllm/worker/__pycache__/__init__.cpython-310.pyc b/vllm/worker/__pycache__/__init__.cpython-310.pyc index 625607bc..e60e8caa 100644 Binary files a/vllm/worker/__pycache__/__init__.cpython-310.pyc and b/vllm/worker/__pycache__/__init__.cpython-310.pyc differ diff --git a/vllm/worker/__pycache__/model_runner_base.cpython-310.pyc b/vllm/worker/__pycache__/model_runner_base.cpython-310.pyc index 41fe8a49..6135ec2a 100644 Binary files a/vllm/worker/__pycache__/model_runner_base.cpython-310.pyc and b/vllm/worker/__pycache__/model_runner_base.cpython-310.pyc differ diff --git a/vllm/worker/__pycache__/worker_base.cpython-310.pyc b/vllm/worker/__pycache__/worker_base.cpython-310.pyc index a1aec6a2..c76efa41 100644 Binary files a/vllm/worker/__pycache__/worker_base.cpython-310.pyc and b/vllm/worker/__pycache__/worker_base.cpython-310.pyc differ