rendezqueue / rendezllama
86%
trunk: 87%

LAST BUILD BRANCH: fix-regen-seed-10117453100447507096
DEFAULT BRANCH: trunk
Repo Added
Files 31
Badge
Embed ▾
README BADGES
x

If you need to use a raster PNG badge, change the '.svg' to '.png' in the link

Markdown

Textile

RDoc

HTML

Rst

LAST BUILD ON BRANCH tmp
branch: tmp
CHANGE BRANCH
x

coverage: 86.427% (-0.5%) from 86.957%
21341850916

push

github

grencez 
feat(option): guess inference thread count

1 of 15 new or added lines in 1 file covered. (6.67%)

1974 of 2284 relevant lines covered (86.43%)

118.03 hits per line

Relevant lines Covered
2284 RELEVANT LINES 1974 COVERED LINES
118.03 HITS PER LINE
Source Files on tmp

Recent builds

Builds Branch Commit Type Ran Committer Via Coverage
21341850916 tmp feat(option): guess inference thread count push grencez github
86.43
21341807490 tmp feat(option): default thread count as physical cores push grencez github
86.43
21335653326 tmp Infer default thread count to match physical cores Introduces `rendezllama::infer_thread_count` to heuristically determine a suitable thread count for inference, aiming to use physical cores rather than logical threads on x86 architectures (by ha... push grencez github
88.7
21254307595 tmp Refactor assistant_cli to use rendezllama classes and reduce verbosity - Rewrote `eg/assistant_cli/main.cc` to use `GlobalScope`, `Vocabulary`, `Inference`, `ChatTrajectory`, and `ChatDisplay`. - Suppressed `llama.cpp` logging using a no-op callb... push grencez github
88.72
21254213748 tmp Refactor assistant_cli to use rendezllama classes and reduce verbosity - Rewrote `eg/assistant_cli/main.cc` to use `GlobalScope`, `Vocabulary`, `Inference`, `ChatTrajectory`, and `ChatDisplay`. - Suppressed `llama.cpp` logging using a no-op callb... push grencez github
88.72
21236360550 tmp Fix assistant_cli: rewrite to use direct llama.h API and fix tokenization Rewrote eg/assistant_cli/main.cc to use the direct llama.h C API, implementing a standard inference loop with KV cache management and sampling. Addressed a critical issue w... push grencez github
88.07
21236314882 tmp Fix assistant_cli: rewrite to use direct llama.h API and fix tokenization Rewrote eg/assistant_cli/main.cc to use the direct llama.h C API, implementing a standard inference loop with KV cache management and sampling. Addressed a critical issue w... push grencez github
88.07
21213160750 tmp Add assistant_cli example push grencez github
88.23
21178338358 tmp qual(cmake): Add chat_guide_cc build target push grencez github
90.79
21177937753 tmp qual(cmake): Add chat_guide_cc build target push grencez github
90.79
See All Builds (1008)