deps: bump llama.cpp — RDNA3/RDNA4 MMQ tile override (+6–8% decode)#3
Closed
DeanoC wants to merge 1 commit into
Closed
deps: bump llama.cpp — RDNA3/RDNA4 MMQ tile override (+6–8% decode)#3DeanoC wants to merge 1 commit into
DeanoC wants to merge 1 commit into
Conversation
Bumps server/deps/llama.cpp (luce-dflash) to pick up the smaller 48x64/4-warp MMQ tile for DFlash spec-decode verify batches on consumer RDNA. Output is bit-identical; decode at --ddtree-budget=22, Qwen3.6-27B Q4_K_M: gfx1201 (R9700): 54.65 -> 59.37 tok/s (+8.3%) gfx1100 (RX 7900 XTX): 56.78 -> 60.18 tok/s (+6.0%) Depends on Luce-Org/lucebox-ggml#18; the submodule SHA should be repointed to the luce-dflash merge commit before this lands. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
DeanoC
force-pushed
the
feat/rdna-mmq-tile-submodule-bump
branch
from
7fe1e25 to
e6023e2
Compare
Collaborator
Author
|
Closing as obsolete: the equivalent upstream change landed in Luce-Org#439. |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Bumps the
server/deps/llama.cppsubmodule (luce-dflash) to pick up the RDNA3/RDNA4 MMQ tile override — a48×64/4-warp tile for DFlash's small spec-decode verify batches in place of the stock128×128/8.Impact (Qwen3.6-27B Q4_K_M,
--ddtree-budget=22, 10-prompt HE mean, n_gen=256, output bit-identical)Dependency / draft status
luce-dflashmerge commit of Add OpenAI-compatible agent-ready server + Blackwell (sm_120/121) support Luce-Org/lucebox-hub#18.Benchmarks measured on the two GPUs above; AI-assisted (Claude Code).