spec : discard last drafted token with low prob#22506
Merged
Merged
Conversation
ServeurpersoCom
approved these changes
Apr 29, 2026
ngxson
approved these changes
Apr 29, 2026
tekintian
added a commit
to tekintian/llama.cpp
that referenced
this pull request
May 1, 2026
* 'master' of github.com:tekintian/llama.cpp: (659 commits) ggml-webgpu: Improve performance of mat-vec and mat-mat for MUL_MAT_ID (ggml-org#22464) Update llama-mmap to use ftello/fseeko (ggml-org#22497) common : check for null getpwuid in hf-cache (ggml-org#22550) vulkan: add get/set tensor 2d functions (ggml-org#22514) spec: fix argument typo (ggml-org#22552) ci : bump ty to 0.0.33 (ggml-org#22535) vendor : update cpp-httplib to 0.43.2 (ggml-org#22548) CUDA: fix tile FA kernel on Pascal (ggml-org#22541) scripts : add wc2wt.sh - create worktree from current HEAD (ggml-org#22513) add fast matmul iquants (ggml-org#22504) spec : fix draft model checkpoints (ggml-org#22521) spec : fix vocab compat checks in spec example (ggml-org#22426) common : do not pass prompt tokens to reasoning budget sampler (ggml-org#22488) hexagon: make vmem and buffer-size configurable (ggml-org#22487) CUDA: fuse SSM_CONV + ADD(bias) + SILU (ggml-org#22478) spec : disacard last drafted token with low prob (ggml-org#22506) sync : ggml ggml : bump version to 0.10.1 (ggml/1469) webui: fix slow mic stop and WAV encode (ggml-org#22480) ggml-cpu : disable tiled matmul on AIX to fix page boundary segfault (ggml-org#22293) ... # Conflicts: # .gitignore
rsenthilkumar6
pushed a commit
to rsenthilkumar6/llama.cpp
that referenced
this pull request
May 1, 2026
samuraieng
pushed a commit
to samuraieng/llama.cpp
that referenced
this pull request
May 6, 2026
ljubomirj
pushed a commit
to ljubomirj/llama.cpp
that referenced
this pull request
May 6, 2026
meh
pushed a commit
to meh/llama.cpp
that referenced
this pull request
May 10, 2026
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.
Overview
In the majority of drafts, the last token is low-prob. For non-recurrent models, it's not a big issue to keep that token. But for recurrent models, this causes the logic to restore checkpoints and re-evaluate the same draft (minus the last token) quite often.
This PR simply discards the low-prob token from the draft. Should result in significant improvement for draft-based speculative decoding for recurrent models due to having to restore the speculative checkpoint less often.
Also fix the stats for drafted/accepted number of tokens - on master, we always incorrectly report 100% acceptance rate.
Requirements