1
86%
trunk: 87%

Ran 25 Jan 2026 04:19PM UTC

Files 31

Run time 0s

Badge

Embed ▾

Committed 25 Jan 2026 04:15PM UTC coverage: 88.704% (-0.02%) from 88.722%

Job # 21335653326.1

Build Type

push

github

Committed by

grencez

Commit Message

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 halving the count if > 4). This avoids oversubscription and improves performance stability.

- Updates `ChatOptions` to initialize `thread_count` using this helper.
- Updates `Inference::commit_to_context` to use `std::thread::hardware_concurrency` (all logical cores) for `batch_thread_count` default, distinct from the physical core preference for generation.
- Updates `assistant_cli` to rely on the `ChatOptions` default instead of manually setting `hardware_concurrency`.
- Shared `infer_thread_count` logic resides in `src/chat/opt.cc` and is exposed via `src/chat/opt.hh`.

Run Details

2128 of 2399 relevant lines covered (88.7%)

523.93 hits per line

rendezqueue / rendezllama / 21335653326 / 1
86%
trunk: 87%

README BADGES
x

Markdown

Textile

RDoc

HTML

Rst

Source Files on job 21335653326.1

rendezqueue / rendezllama / 21335653326 / 1 86% trunk: 87%

README BADGES x

Markdown

Textile

RDoc

HTML

Rst

Source Files on job 21335653326.1

rendezqueue / rendezllama / 21335653326 / 1
86%
trunk: 87%

README BADGES
x