Felipe Cardoso 3686783f4d feat: add --context flag for configurable long-context benchmarks ...

Both run-baseline.sh and run-suite.sh now accept --context N to set
the long-context depth (default: 32768). Prompt tokens auto-scale to
~1/16 of context depth for larger windows.

Examples:
  benchmark run --tag ctx64k --context 65536 --category moe
  benchmark run --tag ctx128k --context 131072 --category moe --reps 3

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-03-26 22:46:16 +01:00

..

compare.sh

fix+test: improve test suite, fix 2 bugs found by tests

2026-03-25 22:22:41 +01:00

run-baseline.sh

feat: add --context flag for configurable long-context benchmarks

2026-03-26 22:46:16 +01:00

run-suite.sh

feat: add --context flag for configurable long-context benchmarks

2026-03-26 22:46:16 +01:00

setup.sh

feat: make llama-rocm-7.2 a required toolbox in benchmark setup

2026-03-26 19:23:03 +01:00