From f11aeed62439b4049b97717401448f29d6561c48 Mon Sep 17 00:00:00 2001 From: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com> Date: Fri, 3 Jan 2025 15:12:39 +0800 Subject: [PATCH] Update gh-pages (#2651) --- _cpp_gen/executor.html | 1126 +++++++++++--- _cpp_gen/runtime.html | 1347 +++++++++-------- _modules/index.html | 3 +- _modules/tensorrt_llm/executor.html | 6 +- _modules/tensorrt_llm/llmapi/llm.html | 3 +- _modules/tensorrt_llm/llmapi/llm_utils.html | 3 +- .../runtime/model_runner_cpp.html | 3 +- _sources/_cpp_gen/executor.rst.txt | 12 +- _sources/_cpp_gen/runtime.rst.txt | 36 +- .../advanced/disaggregated-service.md.txt | 4 +- _sources/index.rst.txt | 1 + .../llm-api-examples/llm_api_examples.rst.txt | 4 +- advanced/disaggregated-service.html | 27 +- advanced/executor.html | 3 +- advanced/expert-parallelism.html | 3 +- advanced/gpt-attention.html | 3 +- advanced/gpt-runtime.html | 3 +- advanced/graph-rewriting.html | 3 +- advanced/inference-request.html | 3 +- advanced/kv-cache-reuse.html | 3 +- advanced/lora.html | 3 +- advanced/speculative-decoding.html | 7 +- advanced/weight-streaming.html | 3 +- architecture/add-model.html | 3 +- architecture/checkpoint.html | 3 +- architecture/core-concepts.html | 3 +- architecture/model-weights-loader.html | 3 +- architecture/overview.html | 3 +- architecture/workflow.html | 3 +- blogs/Falcon180B-H200.html | 3 +- blogs/H100vsA100.html | 3 +- blogs/H200launch.html | 3 +- blogs/XQA-kernel.html | 3 +- blogs/quantization-in-TRT-LLM.html | 3 +- commands/trtllm-build.html | 12 +- commands/trtllm-serve.html | 3 +- genindex.html | 3 +- index.html | 9 +- installation/build-from-source-linux.html | 3 +- installation/build-from-source-windows.html | 3 +- installation/grace-hopper.html | 3 +- installation/linux.html | 3 +- installation/windows.html | 3 +- key-features.html | 3 +- llm-api-examples/customization.html | 3 +- llm-api-examples/index.html | 3 +- llm-api-examples/llm_api_examples.html | 11 +- llm-api-examples/llm_auto_parallel.html | 7 +- llm-api-examples/llm_guided_decoding.html | 7 +- llm-api-examples/llm_inference.html | 7 +- llm-api-examples/llm_inference_async.html | 7 +- .../llm_inference_async_streaming.html | 7 +- llm-api-examples/llm_inference_customize.html | 7 +- .../llm_inference_distributed.html | 7 +- llm-api-examples/llm_logits_processor.html | 7 +- llm-api-examples/llm_lookahead_decoding.html | 7 +- llm-api-examples/llm_medusa_decoding.html | 7 +- llm-api-examples/llm_multilora.html | 7 +- llm-api-examples/llm_quantization.html | 7 +- llm-api/index.html | 3 +- llm-api/reference.html | 3 +- objects.inv | Bin 115396 -> 115372 bytes overview.html | 3 +- performance/perf-analysis.html | 3 +- performance/perf-benchmarking.html | 3 +- performance/perf-best-practices.html | 3 +- performance/perf-overview.html | 7 +- py-modindex.html | 3 +- python-api/tensorrt_llm.functional.html | 3 +- python-api/tensorrt_llm.layers.html | 3 +- python-api/tensorrt_llm.models.html | 3 +- python-api/tensorrt_llm.plugin.html | 3 +- python-api/tensorrt_llm.quantization.html | 3 +- python-api/tensorrt_llm.runtime.html | 3 +- quick-start-guide.html | 3 +- reference/memory.html | 3 +- reference/precision.html | 3 +- reference/support-matrix.html | 3 +- reference/troubleshooting.html | 3 +- release-notes.html | 3 +- search.html | 3 +- searchindex.js | 2 +- 82 files changed, 1827 insertions(+), 1030 deletions(-) diff --git a/_cpp_gen/executor.html b/_cpp_gen/executor.html index 5ea0292f09..e13198b92a 100644 --- a/_cpp_gen/executor.html +++ b/_cpp_gen/executor.html @@ -83,15 +83,718 @@

C++ API

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

Performance

    @@ -180,7 +181,7 @@
    - +