mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-23 07:52:06 +00:00
43df056eee
* (backend) use parking_lot crate for RwLock fairness
# Conflicts:
# backends/trtllm/src/backend.rs
* (launcher) default new server::run parameters to false for now
* (chore) fmt ... why?
* (ffi) use const for GetSamplingConfig
* (server) expose new SchedulingError
* (trt)
* (build) setup ccache if available
* (ffi) add max_new_tokens parameters
* (backend) cleanup a bit
* (backend) expose PullNewTokens
* (ffi) cleanup again
* (ffi) add missing headers imports
* (ffi) add template specialization to catch and convert to Rust Result<T, tensorrt_llm::common::TllmException>
* (looper) new looper initial implementation
* (ffi) remove narrowing type warning
* (ffi) encode the provided user prompt within each request thread
* (misc) change scope identifiers
* (backend) implement the post_processor background thread
* (misc) missing Result types for Rust
* use blocking_recv in looper to consume awaiting_requests at max before pulling in a single step
* (server) forward auth_token to server::run
* (build) fetchcontent use archives instead of git
* (ffi) fix usage of wrong vector constructor making a capacity fill call
* (ffi) missing namespace for tle::Response
* (ffi) do not use reference capture in lambda as we are not capturing anything
* (backend) refactor & cleanup
* (Dockerfile.trtllm) delete for now
* (misc) simplify [make_]move_iterator by using c++20 type inference
* (misc) no need to move for uint32_t items
* (scheduler) rework submit/pull logic
* (post) impl postprocessing
* (misc) delete backend.rs
* (misc) rerun-if-changed all the cmake modules
* (misc) move to latest trtllm
* (fix): HOPPER_SM_MAJOR is 9 not 8
* (misc: build for sm_{75,80,86,89,90} by default
* (misc): build with trtllm 0.13.0
* (misc): increase verbosity of spdlog
* (fix): do not recreate the stateful hashmap at every it
* (misc): update dependency in trtllm dockerfile
* (misc): update dependency in trtllm dockerfile
* (misc): disable logging in release mode
* (misc): improve trtllm download script robustness
* (fix): ore fixes for Dockerfile
* misc(cuda): require 12.6
* chore(cmake): use correct policy for download_timestamp
* feat(looper): check engine and executorWorker paths exist before creating the backend
* chore(cmake): download timestamp should be before URL
* feat(looper): minor optimizations to avoid growing too much the containers
* chore(trtllm): move dockerfile to right place
* chore(trtllm): disable tokenizer parallelism by default
* chore(trtllm): fmt
* chore(trtllm): post-rebase commit
* chore(trtllm): remove unused method
* feat(trtllm): cache maxNumTokens to avoid calling JSON everytime
* misc(router): remove SchedulingError
* feat(trtllm): do not tokenize twice
* Revert "chore(trtllm): remove unused method"
This reverts commit 31747163
* chore(rebase): fix invalid references
* chore(router): add python dependency
* Lint.
* Fix bad rebase
---------
Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
44 lines
2.0 KiB
CMake
44 lines
2.0 KiB
CMake
set(TRT_INCLUDE_DIR ${TGI_TRTLLM_BACKEND_TRT_INCLUDE_DIR})
|
|
set(TRT_LIB_DIR ${TGI_TRTLLM_BACKEND_TRT_LIB_DIR})
|
|
|
|
set(USE_CXX11_ABI ON)
|
|
set(BUILD_PYT OFF)
|
|
set(BUILD_PYBIND OFF)
|
|
set(BUILD_MICRO_BENCHMARKS OFF)
|
|
set(BUILD_BENCHMARKS OFF)
|
|
set(BUILD_TESTS OFF)
|
|
set(CMAKE_CUDA_ARCHITECTURES ${TGI_TRTLLM_BACKEND_TARGET_CUDA_ARCH_LIST})
|
|
|
|
message(STATUS "Building for CUDA Architectures: ${CMAKE_CUDA_ARCHITECTURES}")
|
|
|
|
if (${CMAKE_BUILD_TYPE} STREQUAL "Debug")
|
|
set(FAST_BUILD ON)
|
|
set(NVTX_DISABLE OFF)
|
|
else ()
|
|
set(FAST_BUILD OFF)
|
|
set(FAST_MATH ON)
|
|
set(NVTX_DISABLE ON)
|
|
endif ()
|
|
|
|
fetchcontent_declare(
|
|
trtllm
|
|
GIT_REPOSITORY https://github.com/NVIDIA/TensorRT-LLM.git
|
|
GIT_TAG 201135e58aa525af7e523d091d4c9584229524bc
|
|
GIT_SHALLOW FALSE
|
|
DOWNLOAD_EXTRACT_TIMESTAMP
|
|
)
|
|
fetchcontent_makeavailable(trtllm)
|
|
|
|
message(STATUS "Found TensorRT-LLM: ${trtllm_SOURCE_DIR}")
|
|
execute_process(COMMAND git lfs install WORKING_DIRECTORY "${trtllm_SOURCE_DIR}/")
|
|
execute_process(COMMAND git lfs pull WORKING_DIRECTORY "${trtllm_SOURCE_DIR}/")
|
|
|
|
# TRTLLM use a JIT based *precompiled* library to generate some specific kernels, we are generating the path to this one here
|
|
set(TRTLLM_NVRTC_LIBRARY_NAME "${CMAKE_SHARED_LIBRARY_PREFIX}tensorrt_llm_nvrtc_wrapper${CMAKE_SHARED_LIBRARY_SUFFIX}" CACHE INTERNAL "nvrtc wrapper library name")
|
|
set(TRTLLM_NVRTC_WRAPPER_LIBRARY_PATH "${trtllm_SOURCE_DIR}/cpp/tensorrt_llm/kernels/decoderMaskedMultiheadAttention/decoderXQAImplJIT/nvrtcWrapper/${CMAKE_LIBRARY_ARCHITECTURE}/${TRTLLM_NVRTC_LIBRARY_NAME}"
|
|
CACHE INTERNAL "nvrtc wrapper library path")
|
|
|
|
# The same Executor Static library
|
|
set(TRTLLM_EXECUTOR_STATIC_LIBRARY_NAME "${CMAKE_SHARED_LIBRARY_PREFIX}tensorrt_llm_executor_static${CMAKE_STATIC_LIBRARY_SUFFIX}" CACHE INTERNAL "executor_static library name")
|
|
set(TRTLLM_EXECUTOR_STATIC_LIBRARY_PATH "${trtllm_SOURCE_DIR}/cpp/tensorrt_llm/executor/${CMAKE_LIBRARY_ARCHITECTURE}/${TRTLLM_EXECUTOR_STATIC_LIBRARY_NAME}" CACHE INTERNAL "executor_static library path")
|