cardosofelipe/strix-halo-optimizations
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(benchmark): add --kv-types flag for KV cache quantization sweep

Browse Source
This commit is contained in:
Felipe Cardoso
2026-03-27 12:29:19 +01:00
parent 38daf953bf
commit 7531f6fa74
4 changed files with 176 additions and 82 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
tests/benchmark_flags.bats
View File

@@ -10,6 +10,7 @@ load test_helper.sh
assert_output --partial "--max-size"
assert_output --partial "--category"
assert_output --partial "--skip-longctx"
assert_output --partial "--kv-types"
}
@test "run-suite --help shows usage and exits 0" {
@@ -20,6 +21,7 @@ load test_helper.sh
assert_output --partial "--category"
assert_output --partial "--skip-longctx"
assert_output --partial "--tag"
assert_output --partial "--kv-types"
}
@test "benchmark dispatcher shows help with no args" {
@@ -28,6 +30,7 @@ load test_helper.sh
assert_output --partial "Commands"
assert_output --partial "--max-size"
assert_output --partial "--skip-longctx"
assert_output --partial "--kv-types"
}
@test "benchmark dispatcher passes --help through to baseline" {