Skip to content

[AMD] Optimize kimik2.5-int4-mi300x-vllm, dsr1-fp8-mi300x-sglang #11

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
lishuoshuo-amd wants to merge 1 commit into
base: main
Choose a base branch
from
+15 −3
Open

[AMD] Optimize kimik2.5-int4-mi300x-vllm, dsr1-fp8-mi300x-sglang #11

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions benchmarks/single_node/dsr1_fp8_mi300x.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,10 +48,10 @@ set -x
python3 -m sglang.launch_server \
--model-path=$MODEL --host=0.0.0.0 --port=$PORT --trust-remote-code \
--tensor-parallel-size=$TP \
--mem-fraction-static=0.8 \
--mem-fraction-static=0.85 \
--cuda-graph-max-bs=128 \
--chunked-prefill-size=131072 \
--num-continuous-decode-steps=4 \
--num-continuous-decode-steps=16 \
--max-prefill-tokens=131072 \
--kv-cache-dtype fp8_e4m3 \
--attention-backend aiter \
Expand Down
2 changes: 1 addition & 1 deletion benchmarks/single_node/kimik2.5_int4_mi300x.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,7 +45,7 @@ vllm serve $MODEL --port $PORT \
--block-size=64 \
--trust-remote-code \
--no-enable-prefix-caching \
--max-num-seqs 256 \
--max-num-seqs 128 \
--mm-encoder-tp-mode data > $SERVER_LOG 2>&1 &

SERVER_PID=$!
Expand Down
12 changes: 12 additions & 0 deletions perf-changelog.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,15 @@
- config-keys:
- kimik2.5-int4-mi300x-vllm
description:
- "Tune --max-num-seqs 256 → 128 (+34.2% avg output throughput gain)"
pr-link: TBD

- config-keys:
- dsr1-fp8-mi300x-sglang
description:
- "Tune --mem-fraction-static 0.8 → 0.85, --num-continuous-decode-steps 4 → 16 (+4.2% avg output throughput gain)"
pr-link: TBD

- config-keys:
- kimik2.5-fp4-gb200-dynamo-trt
description:
Expand Down
Loading