Update benchmark documentation after harness replacement
This commit is contained in:
1 parent
863897f92a
commit
c02d67513d
2 files changed
+4
-2
No files matched your search
@@ -253,7 +253,7 @@ ngram draft costs its own forward pass / occupancy without adding enough
|
|||||||
accepted tokens on top of MTP. Baseline (no ngram) remains the production
|
accepted tokens on top of MTP. Baseline (no ngram) remains the production
|
||||||
config (`--spec-type draft-mtp` only). Keep ngram-mod off.
|
config (`--spec-type draft-mtp` only). Keep ngram-mod off.
|
||||||
|
|
||||||
The harness lives at [scripts/bench-spec-stack.sh](../../scripts/bench-spec-stack.sh);
|
The historical harness was moved to `.AGENTTRASH/bench-scripts-20260901/` and is retained for audit only.
|
||||||
it boots the v3 stack on a scratch port and reads authoritative
|
it boots the v3 stack on a scratch port and reads authoritative
|
||||||
`print_timing` lines. It requires the production service to be stopped.
|
`print_timing` lines. It requires the production service to be stopped.
|
||||||
|
|
||||||
|
|||||||
@@ -142,7 +142,9 @@ Decode throughput depends on the ubatch (per-eval token batch). Run the sweep
|
|||||||
on 8k contexts, 512 → 4096 in steps of 512, with a fixed batch:
|
on 8k contexts, 512 → 4096 in steps of 512, with a fixed batch:
|
||||||
|
|
||||||
```
|
```
|
||||||
STOPSVC=1 ./scripts/bench-ubatch-rocmi4.sh
|
sudo systemctl stop frank-default-large
|
||||||
|
./scripts/bench-ubatch.sh
|
||||||
|
sudo systemctl start frank-default-large
|
||||||
```
|
```
|
||||||
|
|
||||||
The script stops `frank-default-large` for a clean GPU, boots one server
|
The script stops `frank-default-large` for a clean GPU, boots one server
|
||||||
|
|||||||
Reference in new issue
Block a user