frank-default-small: 491520 context pool (163840 per slot x 3)
--ctx-size is the total pool divided among --parallel slots, so with PARALLEL=3 the 160k target must be a 491520 pool (163840/slot) to actually deliver 160k context per slot. Env, serve default, bats updated.
This commit is contained in:
1 parent
04a8fb7806
commit
8f860d24a6
3 files changed
+10
-8
No files matched your search
@@ -14,9 +14,10 @@ TEMPLATE_FILE="$REPO_ROOT/scripts/chat-template.jinja"
|
||||
grep -q 'Ornith-1\.5-35B-A3B-CRACK-Q8_0\.gguf' "$SERVE_FILE"
|
||||
}
|
||||
|
||||
@test "frank-default-small uses three 160000 context slots" {
|
||||
grep -q '^CTX_SIZE=160000$' "$ENV_FILE"
|
||||
@test "frank-default-small uses three 163840-slot context (491520 pool)" {
|
||||
grep -q '^CTX_SIZE=491520$' "$ENV_FILE"
|
||||
grep -q '^PARALLEL=3$' "$ENV_FILE"
|
||||
grep -q '163840 per slot' "$ENV_FILE"
|
||||
}
|
||||
|
||||
@test "frank-default-small uses K q8_0 + V q5_0 KV cache with Hadamard" {
|
||||
|
||||
Reference in new issue
Block a user