server : fix incorrect num_tokens_predicted #3480
Merged
Conversation
This file contains hidden or 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
ggerganov
approved these changes
Oct 5, 2023
joelkuiper
added a commit
to vortext/llama.cpp
that referenced
this pull request
Oct 6, 2023
…example * 'master' of github.com:ggerganov/llama.cpp: kv cache slot search improvements (ggml-org#3493) prompts : fix editorconfig checks after ggml-org#3416 parallel : add option to load external prompt file (ggml-org#3416) server : reuse llama_sample_token common util (ggml-org#3494) llama : correct hparams comparison (ggml-org#3446) ci : fix xcodebuild destinations (ggml-org#3491) convert : update Falcon script for new HF config (ggml-org#3448) build : use std::make_tuple() for compatibility with older GCC versions (ggml-org#3488) common : process escape sequences in reverse prompts (ggml-org#3461) CLBlast: Fix handling of on-device tensor data server : fix incorrect num_tokens_predicted (ggml-org#3480) swift : disable ACCELERATE_NEW_LAPACK (ggml-org#3481) ci : add swift build via xcodebuild (ggml-org#3482)
yusiwen
pushed a commit
to yusiwen/llama.cpp
that referenced
this pull request
Oct 7, 2023
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Outdated suggestions cannot be applied.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.
format_timings, the assertion might be wrong because n_eval is not equal to the count of generated tokens. For instance we set n_batch = 1, the count oftimings.n_evalwill include prompt.