sampling : avoid expensive softmax during greedy sampling #9605
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
slaren
reviewed
Sep 23, 2024
Co-authored-by: slaren <[email protected]>
slaren
approved these changes
Sep 23, 2024
dsx1986
pushed a commit
to dsx1986/llama.cpp
that referenced
this pull request
Oct 29, 2024
) * sampling : avoid expensive softmax during greedy sampling ggml-ci * speculative : fix default RNG seed + set sparams.n_probs * Update tests/test-sampling.cpp Co-authored-by: slaren <[email protected]> * sampling : add clarifying comment [no ci] --------- Co-authored-by: slaren <[email protected]>
arthw
pushed a commit
to arthw/llama.cpp
that referenced
this pull request
Nov 15, 2024
) * sampling : avoid expensive softmax during greedy sampling ggml-ci * speculative : fix default RNG seed + set sparams.n_probs * Update tests/test-sampling.cpp Co-authored-by: slaren <[email protected]> * sampling : add clarifying comment [no ci] --------- Co-authored-by: slaren <[email protected]>
arthw
pushed a commit
to arthw/llama.cpp
that referenced
this pull request
Nov 18, 2024
) * sampling : avoid expensive softmax during greedy sampling ggml-ci * speculative : fix default RNG seed + set sparams.n_probs * Update tests/test-sampling.cpp Co-authored-by: slaren <[email protected]> * sampling : add clarifying comment [no ci] --------- Co-authored-by: slaren <[email protected]>
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Outdated suggestions cannot be applied.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.
fix #9530
When the temperature is non-positive, we can simply sample greedily the token with the highest logit. But in some cases, the probs of the secondary tokens are also required (e.g.
llama-serverto display candidate probs,llama-speculativeto peform stochastic speculative sampling). In such cases, we first filter the the topsparams.n_probstokens via atop-ksampler and then apply softmax to them in order to avoid sorting the full vocabulary.Also add perf timings to
test-samplingto keep track of the performance of the samplers.ggml-ci