Skip to content

Disable prefix caching for mi300 & mi325 qwen3.5 & glm5 AMD benchmarks #970

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

Merged
functionstackx merged 4 commits into from
Mar 29, 2026
+17 −4
Merged

Disable prefix caching for mi300 & mi325 qwen3.5 & glm5 AMD benchmarks #970

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
dd77d6f
Disable prefix caching for qwen3.5 & glm5 AMD benchmarks
github-actions[bot] Mar 28, 2026
3fbe29f
Add perf-changelog.yaml entry for --disable-radix-cache on qwen3.5 & …
github-actions[bot] Mar 28, 2026
9d8f97c
Remove MI355X changes, keep --disable-radix-cache for MI300X & MI325X…
github-actions[bot] Mar 29, 2026
f646f6b
Move perf-changelog entry to end of file
github-actions[bot] Mar 29, 2026
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
3 changes: 2 additions & 1 deletion benchmarks/single_node/qwen3.5_bf16_mi300x.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,8 @@ python3 -m sglang.launch_server \
--port $PORT \
--tensor-parallel-size $TP \
--trust-remote-code \
--mem-fraction-static 0.8 $EVAL_CONTEXT_ARGS > $SERVER_LOG 2>&1 &
--mem-fraction-static 0.8 \
--disable-radix-cache $EVAL_CONTEXT_ARGS > $SERVER_LOG 2>&1 &

SERVER_PID=$!

Expand Down
3 changes: 2 additions & 1 deletion benchmarks/single_node/qwen3.5_bf16_mi325x.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,8 @@ python3 -m sglang.launch_server \
--port $PORT \
--tensor-parallel-size $TP \
--trust-remote-code \
--mem-fraction-static 0.8 $EVAL_CONTEXT_ARGS > $SERVER_LOG 2>&1 &
--mem-fraction-static 0.8 \
--disable-radix-cache $EVAL_CONTEXT_ARGS > $SERVER_LOG 2>&1 &

SERVER_PID=$!

Expand Down
3 changes: 2 additions & 1 deletion benchmarks/single_node/qwen3.5_fp8_mi300x.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,7 +37,8 @@ python3 -m sglang.launch_server \
--port $PORT \
--tensor-parallel-size $TP \
--trust-remote-code \
--mem-fraction-static 0.8 $EVAL_CONTEXT_ARGS > $SERVER_LOG 2>&1 &
--mem-fraction-static 0.8 \
--disable-radix-cache $EVAL_CONTEXT_ARGS > $SERVER_LOG 2>&1 &

SERVER_PID=$!

Expand Down
3 changes: 2 additions & 1 deletion benchmarks/single_node/qwen3.5_fp8_mi325x.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,7 +37,8 @@ python3 -m sglang.launch_server \
--port $PORT \
--tensor-parallel-size $TP \
--trust-remote-code \
--mem-fraction-static 0.8 $EVAL_CONTEXT_ARGS > $SERVER_LOG 2>&1 &
--mem-fraction-static 0.8 \
--disable-radix-cache $EVAL_CONTEXT_ARGS > $SERVER_LOG 2>&1 &

SERVER_PID=$!

Expand Down
9 changes: 9 additions & 0 deletions perf-changelog.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1189,3 +1189,12 @@
- "Separate evals, change to 8k1k, fail loudly, 5-shot, top of curve & middle of curve"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/911
evals-only: true

- config-keys:
- qwen3.5-bf16-mi300x-sglang
- qwen3.5-bf16-mi325x-sglang
- qwen3.5-fp8-mi300x-sglang
- qwen3.5-fp8-mi325x-sglang
description:
- "Add --disable-radix-cache to SGLang server launch command for qwen3.5 MI300X and MI325X benchmark scripts"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/970
Loading