Skip to content

[TRTLLM-15405][refactor] BREAKING: Remove TRTLLMSampler and sampler_type #18223

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
zhaoyangwang-nvidia wants to merge 1 commit into from
Closed

[TRTLLM-15405][refactor] BREAKING: Remove TRTLLMSampler and sampler_type #18223

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 0 additions & 4 deletions .pre-commit-config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -306,7 +306,6 @@ common-files: &common_files |
tensorrt_llm/_torch/pyexecutor/kv_cache_transceiver.py |
tensorrt_llm/_torch/pyexecutor/layerwise_nvtx_marker.py |
tensorrt_llm/_torch/pyexecutor/llm_request.py |
tensorrt_llm/_torch/pyexecutor/make_decoding_batch_input_output.py |
tensorrt_llm/_torch/pyexecutor/mamba_cache_manager.py |
tensorrt_llm/_torch/pyexecutor/model_engine.py |
tensorrt_llm/_torch/pyexecutor/model_loader.py |
Expand Down Expand Up @@ -619,7 +618,6 @@ common-files: &common_files |
tests/unittest/_torch/ray_orchestrator/single_gpu/test_cache_transceiver_comm.py |
tests/unittest/_torch/sampler/test_beam_search.py |
tests/unittest/_torch/sampler/test_best_of_n.py |
tests/unittest/_torch/sampler/test_trtllm_sampler.py |
tests/unittest/_torch/speculative/test_eagle3.py |
tests/unittest/_torch/test_connector.py |
tests/unittest/_torch/test_torch_multi_arange.py |
Expand Down Expand Up @@ -1072,7 +1070,6 @@ legacy-files: &legacy_files |
tensorrt_llm/_torch/pyexecutor/kv_cache_transceiver.py |
tensorrt_llm/_torch/pyexecutor/layerwise_nvtx_marker.py |
tensorrt_llm/_torch/pyexecutor/llm_request.py |
tensorrt_llm/_torch/pyexecutor/make_decoding_batch_input_output.py |
tensorrt_llm/_torch/pyexecutor/mamba_cache_manager.py |
tensorrt_llm/_torch/pyexecutor/model_engine.py |
tensorrt_llm/_torch/pyexecutor/model_loader.py |
Expand Down Expand Up @@ -1385,7 +1382,6 @@ legacy-files: &legacy_files |
tests/unittest/_torch/ray_orchestrator/single_gpu/test_cache_transceiver_comm.py |
tests/unittest/_torch/sampler/test_beam_search.py |
tests/unittest/_torch/sampler/test_best_of_n.py |
tests/unittest/_torch/sampler/test_trtllm_sampler.py |
tests/unittest/_torch/speculative/test_eagle3.py |
tests/unittest/_torch/test_connector.py |
tests/unittest/_torch/test_torch_multi_arange.py |
Expand Down
88 changes: 0 additions & 88 deletions cpp/include/tensorrt_llm/batch_manager/createNewDecoderRequests.h
View file
Open in desktop

This file was deleted.

186 changes: 0 additions & 186 deletions cpp/include/tensorrt_llm/batch_manager/decoderBuffers.h
View file
Open in desktop

This file was deleted.

66 changes: 0 additions & 66 deletions cpp/include/tensorrt_llm/batch_manager/medusaBuffers.h
View file
Open in desktop

This file was deleted.

5 changes: 5 additions & 0 deletions cpp/include/tensorrt_llm/executor/executor.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,6 +63,11 @@ class DataTransceiverState;
class SamplingConfig
{
public:
/// @brief Largest beam width a request may ask for.
static constexpr SizeType32 kMaxBeamWidth = 1024;
/// @brief Largest variable-beam-width schedule (beamWidthArray) a request may supply.
static constexpr SizeType32 kMaxBeamWidthArrayLength = 8;

/// @brief Constructor for SamplingConfig
/// See description of parameters below
explicit SamplingConfig(SizeType32 beamWidth = 1, std::optional<SizeType32> const& topK = std::nullopt,
Expand Down
Loading
Loading