chore [BREAKING CHANGE]: Flatten PyTorchConfig knobs into TorchLlmArgs

docs/source/blogs/Best_perf_practice_on_DeepSeek-R1_in_TensorRT-LLM.md

@@ -134,9 +134,8 @@ To do the benchmark, run the following command:
 YOUR_DATA_PATH=<your dataset file following the format>
 
 cat >./extra-llm-api-config.yml<<EOF
-pytorch_backend_config:
-    use_cuda_graph: true
-    moe_backend: TRTLLM
+use_cuda_graph: true
+moe_backend: TRTLLM
 speculative_config:
     decoding_type: MTP
     num_nextn_predict_layers: 3
@@ -202,21 +201,20 @@ python ${YOUR_WORK_PATH}/benchmarks/cpp/prepare_dataset.py \
 YOUR_DATA_PATH=./dataset.txt
 
 cat >./extra-llm-api-config.yml <<EOF
-pytorch_backend_config:
-    use_cuda_graph: true
-    cuda_graph_padding_enabled: true
-    cuda_graph_batch_sizes:
-    - 1
-    - 2
-    - 4
-    - 8
-    - 16
-    - 32
-    - 64
-    - 128
-    - 256
-    - 384
-    print_iter_log: true
+use_cuda_graph: true
+cuda_graph_padding_enabled: true
+cuda_graph_batch_sizes:
+- 1
+- 2
+- 4
+- 8
+- 16
+- 32
+- 64
+- 128
+- 256
+- 384
+print_iter_log: true
 enable_attention_dp: true
 EOF
 
@@ -257,8 +255,7 @@ To do the benchmark, run the following command:
 YOUR_DATA_PATH=<your dataset file following the format>
 
 cat >./extra-llm-api-config.yml<<EOF
-pytorch_backend_config:
-    use_cuda_graph: true
+use_cuda_graph: true
 speculative_config:
     decoding_type: MTP
     num_nextn_predict_layers: 3
@@ -307,10 +304,9 @@ python ${YOUR_WORK_PATH}/benchmarks/cpp/prepare_dataset.py \
 YOUR_DATA_PATH=./dataset.txt
 
 cat >./extra-llm-api-config.yml<<EOF
-pytorch_backend_config:
-    use_cuda_graph: true
-    cuda_graph_batch_sizes:
-    - 128
+use_cuda_graph: true
+cuda_graph_batch_sizes:
+- 128
 enable_attention_dp: true
 EOF
 

docs/source/blogs/tech_blog/blog2_DeepSeek_R1_MTP_Implementation_and_Optimization.md

@@ -121,9 +121,8 @@ To benchmark min-latency performance with MTP, you need to follow [this document
 YOUR_DATA_PATH=<your dataset file following the format>
 
 cat >./extra-llm-api-config.yml<<EOF
-pytorch_backend_config:
-    use_cuda_graph: true
-    moe_backend: TRTLLM
+use_cuda_graph: true
+moe_backend: TRTLLM
 speculative_config:
     decoding_type: MTP
     num_nextn_predict_layers: 3
@@ -177,9 +176,8 @@ To benchmark min-latency performance with MTP Relaxed Acceptance, you need to fo
 YOUR_DATA_PATH=<your dataset file following the format>
 
 cat >./extra-llm-api-config.yml<<EOF
-pytorch_backend_config:
-    use_cuda_graph: true
-    moe_backend: TRTLLM
+use_cuda_graph: true
+moe_backend: TRTLLM
 speculative_config:
     decoding_type: MTP
     num_nextn_predict_layers: 3

docs/source/performance/perf-benchmarking.md

@@ -628,8 +628,7 @@ If you would like to force the KV cache quantizaton, you can specify the followi
 when the checkpoint precision is `null`:
 
 ```yaml
-pytorch_backend_config:
-  kv_cache_dtype: "fp8"
+kv_cache_dtype: "fp8"
 ```
 
 ```{tip}

docs/source/performance/perf-overview.md

@@ -200,11 +200,9 @@ trtllm-bench --model $model_name throughput --dataset $dataset_file --backend py
 
 `llm_options.yml`
 ```yaml
-
- pytorch_backend_config:
-  use_cuda_graph: true
-  cuda_graph_padding_enabled: true
-  cuda_graph_batch_sizes:
+use_cuda_graph: true
+cuda_graph_padding_enabled: true
+cuda_graph_batch_sizes:
   - 1
   - 2
   - 4

docs/source/torch/attention.md

@@ -16,7 +16,7 @@ The following sections explain how to use these implementations and provide a br
 
 
 There are currently three available attention backends: the vanilla backend, the TRT-LLM backend, and the Flashinfer backend.
-You can specify the desired attention backend using `PyTorchConfig.attn_backend`. For instance, to utilize the Flashinfer backend, you can create a `PyTorchConfig` with `attn_backend = "flashinfer"` and then pass it to the `LLM` constructor as follows: `LLM(pytorch_backend_config=pytorch_config)`. This will enable the use of the Flashinfer backend for your model.
+You can specify the desired attention backend using `PyTorchConfig.attn_backend`. For instance, to utilize the Flashinfer backend, you can pass `attn_backend="flashinfer"` to the `LLM` constructor as follows: `LLM(attn_backend="flashinfer")`. This will enable the use of the Flashinfer backend for your model.
 
 The vanilla backend, `VanillaAttention`, is a reference implementation designed primarily for inflight batching and linear KV cache support. While it serves as a useful baseline, it is not recommended for production use due to its limited optimizations.
 

examples/auto_deploy/README.md

@@ -265,7 +265,7 @@ llm = LLM(
     model=<HF_MODEL_CARD_OR_DIR>,
     backend="autodeploy",
     build_config=build_config,
-    pytorch_backend_config=ad_config,
+    auto_deploy_config=ad_config,
     tensor_parallel_size=<NUM_WORLD_RANK>,
 )
 

examples/auto_deploy/build_and_run_ad.py

@@ -73,7 +73,7 @@ def build_llm_from_config(config: SimpleConfig) -> LLM:
         model=factory.model,
         backend="autodeploy",
         build_config=build_config,
-        pytorch_backend_config=ad_config,
+        auto_deploy_config=ad_config,
         tensor_parallel_size=config.world_size,
         tokenizer=factory.init_tokenizer() if config.customize_tokenizer else None,
     )

examples/disaggregated/README.md

@@ -9,7 +9,7 @@ You can use multiple `trtllm-serve` commands to launch the context and generatio
 for disaggregated serving. For example, you could launch two context servers and one generation servers as follows:
 
 ```
-echo -e "pytorch_backend_config:\n  disable_overlap_scheduler: True\ncache_transceiver_config:\n  max_num_tokens: 2048" > context_extra-llm-api-config.yml
+echo -e "disable_overlap_scheduler: True\ncache_transceiver_config:\nmax_num_tokens: 2048" > context_extra-llm-api-config.yml
 echo -e "cache_transceiver_config:\n  max_num_tokens: 2048" > gen_extra-llm-api-config.yml
 
 export TRTLLM_USE_UCX_KVCACHE=1
@@ -63,9 +63,8 @@ hostname: localhost
 port: 8000
 model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
 backend: "pytorch"
-pytorch_backend_config:
-  use_cuda_graph: False
-  disable_overlap_scheduler: True
+use_cuda_graph: False
+disable_overlap_scheduler: True
 context_servers:
   num_instances: 1
   tensor_parallel_size: 1

examples/disaggregated/disagg_config.yaml

@@ -3,9 +3,8 @@ port: 8000
 model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
 free_gpu_memory_fraction: 0.25
 backend: "pytorch"
-pytorch_backend_config:
-  use_cuda_graph: False
-  disable_overlap_scheduler: True
+use_cuda_graph: False
+disable_overlap_scheduler: True
 context_servers:
   num_instances: 1
   tensor_parallel_size: 1

examples/llm-api/llm_inference_kv_events.py

@@ -1,17 +1,15 @@
 ### Get KV Cache Events
 
 from tensorrt_llm import LLM, SamplingParams
-from tensorrt_llm._torch.pyexecutor.config import PyTorchConfig
 from tensorrt_llm.llmapi import KvCacheConfig
 
 
 def main():
-    pytorch_config = PyTorchConfig(autotuner_enabled=False,
-                                   kv_cache_dtype='auto')
 
     llm = LLM(model="TinyLlama/TinyLlama-1.1B-Chat-v1.0",
               tensor_parallel_size=2,
-              pytorch_backend_config=pytorch_config,
+              autotuner_enabled=False,
+              kv_cache_dtype='auto',
               kv_cache_config=KvCacheConfig(enable_block_reuse=True,
                                             event_buffer_max_size=1024),
               backend="pytorch")

examples/llm-api/llm_mgmn_trtllm_bench.sh

@@ -74,10 +74,9 @@ srun -l \
 
         # This is optional
         cat > /tmp/pytorch_extra_args.txt << EOF
-pytorch_backend_config:
-    use_cuda_graph: false
-    cuda_graph_padding_enabled: false
-    print_iter_log: true
+use_cuda_graph: false
+cuda_graph_padding_enabled: false
+print_iter_log: true
 enable_attention_dp: false
 EOF
 

examples/llm-eval/lm-eval-harness/lm_eval_tensorrt_llm.py

@@ -100,7 +100,6 @@ def __init__(
             if hasattr(PyTorchConfig, "moe_backend"):
                 pytorch_config_params["moe_backend"] = self.moe_backend
                 print(f"Info: moe_backend is set to {self.moe_backend}")
-            pytorch_config = PyTorchConfig(**pytorch_config_params)
 
             # stop words not currently supported by torch backend
             self.use_stop_words = False
@@ -110,7 +109,7 @@ def __init__(
                 tensor_parallel_size=tp,
                 trust_remote_code=trust_remote_code,
                 enable_chunked_prefill=False,
-                pytorch_backend_config=pytorch_config,
+                **pytorch_config_params,
                 tokenizer=self.tokenizer,
                 kv_cache_config=trt_kv_cache_config,
                 moe_expert_parallel_size=self.moe_expert_parallel_size,

examples/models/core/deepseek_v3/README.md

@@ -140,10 +140,9 @@ python /app/tensorrt_llm/benchmarks/cpp/prepare_dataset.py \
         --num-requests 24 > /tmp/benchmarking_64k.txt
 
 cat <<EOF > /tmp/extra-llm-api-config.yml
-pytorch_backend_config:
-  use_cuda_graph: true
-  cuda_graph_padding_enabled: true
-  cuda_graph_batch_sizes: [1, 4, 8, 12]
+use_cuda_graph: true
+cuda_graph_padding_enabled: true
+cuda_graph_batch_sizes: [1, 4, 8, 12]
 EOF
 
 trtllm-bench -m deepseek-ai/DeepSeek-R1 --model_path ${DS_R1_NVFP4_MODEL_PATH} throughput \
@@ -168,11 +167,10 @@ python /app/tensorrt_llm/benchmarks/cpp/prepare_dataset.py \
         --num-requests 4 > /tmp/benchmarking_128k.txt
 
 cat <<EOF > /tmp/extra-llm-api-config.yml
-pytorch_backend_config:
-  use_cuda_graph: true
-  cuda_graph_padding_enabled: true
-  cuda_graph_batch_sizes: [1, 2]
-  moe_max_num_tokens: 16384
+use_cuda_graph: true
+cuda_graph_padding_enabled: true
+cuda_graph_batch_sizes: [1, 2]
+moe_max_num_tokens: 16384
 EOF
 
 trtllm-bench -m deepseek-ai/DeepSeek-R1 --model_path ${DS_R1_NVFP4_MODEL_PATH} throughput \
@@ -193,8 +191,7 @@ Evaluate the model accuracy using `trtllm-eval`.
 1. (Optional) Prepare an advanced configuration file:
 ```bash
 cat >./extra-llm-api-config.yml <<EOF
-pytorch_backend_config:
-    use_cuda_graph: true
+use_cuda_graph: true
 enable_attention_dp: true
 EOF
 ```
@@ -236,21 +233,20 @@ To serve the model using `trtllm-serve`:
 
 ```bash
 cat >./extra-llm-api-config.yml <<EOF
-pytorch_backend_config:
-    use_cuda_graph: true
-    cuda_graph_padding_enabled: true
-    cuda_graph_batch_sizes:
-    - 1
-    - 2
-    - 4
-    - 8
-    - 16
-    - 32
-    - 64
-    - 128
-    - 256
-    - 384
-    print_iter_log: true
+use_cuda_graph: true
+cuda_graph_padding_enabled: true
+cuda_graph_batch_sizes:
+  - 1
+  - 2
+  - 4
+  - 8
+  - 16
+  - 32
+  - 64
+  - 128
+  - 256
+  - 384
+print_iter_log: true
 enable_attention_dp: true
 EOF
 
@@ -427,21 +423,20 @@ python3 /path/to/TensorRT-LLM/benchmarks/cpp/prepare_dataset.py \
     --input-mean=1024 --output-mean=2048 --input-stdev=0 --output-stdev=0 > /tmp/dataset.txt
 
 cat >/path/to/TensorRT-LLM/extra-llm-api-config.yml <<EOF
-pytorch_backend_config:
-    use_cuda_graph: true
-    cuda_graph_padding_enabled: true
-    cuda_graph_batch_sizes:
-    - 1
-    - 2
-    - 4
-    - 8
-    - 16
-    - 32
-    - 64
-    - 128
-    - 256
-    - 384
-    print_iter_log: true
+use_cuda_graph: true
+cuda_graph_padding_enabled: true
+cuda_graph_batch_sizes:
+  - 1
+  - 2
+  - 4
+  - 8
+  - 16
+  - 32
+  - 64
+  - 128
+  - 256
+  - 384
+print_iter_log: true
 enable_attention_dp: true
 EOF
 ```
@@ -605,9 +600,8 @@ To enable FP8 MLA, modify the `kv_cache_quant_algo` property. The following show
 Alternatively, configure FP8 MLA through the `kv_cache_dtype` of the PyTorch backend config. An example is to use `--kv_cache_dtype` of `quickstart_advanced.py`. Also, you can edit `extra-llm-api-config.yml` consumed by `--extra_llm_api_options` of `trtllm-serve`, `trtllm-bench` and so on:
 ```yaml
 # ...
-pytorch_backend_config:
-  kv_cache_dtype: fp8
-  # ...
+kv_cache_dtype: fp8
+# ...
 ```
 
 ### W4AFP8

examples/models/core/qwen/README.md

@@ -653,21 +653,20 @@ To serve the model using `trtllm-serve`:
 
 ```bash
 cat >./extra-llm-api-config.yml <<EOF
-pytorch_backend_config:
-    use_cuda_graph: true
-    cuda_graph_padding_enabled: true
-    cuda_graph_batch_sizes:
-    - 1
-    - 2
-    - 4
-    - 8
-    - 16
-    - 32
-    - 64
-    - 128
-    - 256
-    - 384
-    print_iter_log: true
+use_cuda_graph: true
+cuda_graph_padding_enabled: true
+cuda_graph_batch_sizes:
+- 1
+- 2
+- 4
+- 8
+- 16
+- 32
+- 64
+- 128
+- 256
+- 384
+print_iter_log: true
 enable_attention_dp: true
 EOF