feat: tiktoken integration #60
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
nguyenhoangthuan99
force-pushed
the
feat-tiktoken-integration
branch
from
de955c1
to
5a4a79c
Compare
cpp/tensorrt_llm/cortex.tensorrt-llm/src/tensorrt-llm_engine.cc
Outdated
Show resolved
Hide resolved
cpp/tensorrt_llm/cortex.tensorrt-llm/src/tensorrt-llm_engine.cc
Outdated
Show resolved
Hide resolved
nguyenhoangthuan99
force-pushed
the
feat-tiktoken-integration
branch
from
53fe0f1
to
2f48d96
Compare
nguyenhoangthuan99
force-pushed
the
feat-tiktoken-integration
branch
from
658faf2
to
a3f66a7
Compare
nguyenhoangthuan99
force-pushed
the
feat-tiktoken-integration
branch
from
8ce43e7
to
b4ddb21
Compare
vansangpfiev
added a commit
that referenced
this pull request
Jul 25, 2024
* TensorRT-LLM v0.10 update * TensorRT-LLM Release 0.10.0 --------- Co-authored-by: Loki <lokravi@amazon.com> Co-authored-by: meghagarwal <16129366+megha95@users.noreply.github.com> * Update Makefile and CICD for rel 0.10.0 * Update breaking change for 0.10.0 * fix: use tensorrt 10.1.0 * fix: revert tensorrt version windows * fix: synk report fixup (#56) Co-authored-by: vansangpfiev <sang@jan.ai> * Fix error read timeout minio * feat: tiktoken integration (#60) * cpp-tiktoken integration init * remove cpp-tiktoken folder * tiktoken integration init * move fmt to third-party dependency * remove unnecessary option in cortex CMakeLists * remove unnecessary submodule * make pcre2 as third-party lib * fix CI bug build in window * fix CI bug in linux * link directory pcre2 * Fix CI bug in linux 'pcre2.h' not found * Fix bug build static third party lib * Integate Llama3 successfully * refactor with model type * remove unnecessary comment * format and code convention * fix logic of mistral when preparing input * Add remove end_of_text and end_of_turn token feature for llama3 * fix: patch pcre2 CMakeLists.txt file * fix: do not add fPIC to cpp-tiktoken cmake file * fix: suppress warnings * fix: add CMAKE_C_FLAGS * fix: CI bug build for window in cpp-tiktoken * fix: CI bug for window fmt build fail without utf-8 flag * fix: CI bug for window stop using fmt * fix: build bugs for window - using latest pcre2 third party * fix: build bugs for window - pcre2 static runtime on * fix CI bug for window build pcre2 * rename link lib to pcre2-8-static in windows * fix: use pcre2 dynamic lib for windows * fix: pack tensorrt_llm_nvrtc_wrapper.dll * test: only windows * fix: disable setLoggerFinder for msvc * fix: cleanup cmake files * fix: remove fmt * fix: pack libtensorrt_llm_nvrtc_wrapper * fix: patches windows * fix: rm fmt --------- Co-authored-by: sangjanai <sang@jan.ai> --------- Co-authored-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com> Co-authored-by: Loki <lokravi@amazon.com> Co-authored-by: meghagarwal <16129366+megha95@users.noreply.github.com> Co-authored-by: Hien To <tominhhien97@gmail.com> Co-authored-by: sangjanai <sang@jan.ai> Co-authored-by: vansangpfiev <vansangpfiev@gmail.com> Co-authored-by: nguyenhoangthuan99 <35255081+nguyenhoangthuan99@users.noreply.github.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Issue: #49