Use GenAI text streamer implementation #3030
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
mzegla
commented
Feb 10, 2025
| printLen = 0; | ||
| return chunk; | ||
| int64_t print_until = m_decoded_lengths[m_decoded_lengths.size() - delay_n_tokens]; | ||
| if (print_until != -1 && print_until > static_cast<int64_t>(m_printed_len)) { |
There was a problem hiding this comment.
GenAI implementation does not have this static cast. We have an error when building without it.
mzegla
commented
Feb 10, 2025
| printLen = lastSpacePos + 1; | ||
| SPDLOG_LOGGER_TRACE(llm_calculator_logger, "Generated tokens: {}", tokenCache); | ||
| return chunk; | ||
| constexpr char replacement[] = "\xef\xbf\xbd"; // MSVC with /utf-8 fails to compile <UNK> directly with newline in string literal error. |
There was a problem hiding this comment.
In this comment, GenAI contains special character instead of <UNK>. I had to replace it, so our pipeline passes.
mzegla
force-pushed
the
genai_streamer
branch
from
bbc2ef7 to
9cddc22
Compare
dkalinowski
approved these changes
Feb 10, 2025
michalkulakowski
approved these changes
Feb 10, 2025
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Outdated suggestions cannot be applied.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.
Switching text streamer to GenAI implementation. For now we adapt a copy since it's not in GenAI interface now.
This will likely be useful for streaming enablement in pipelines other than ContinuousBatchingPipeline.