Skip to content

[Hyperloom] Optimize dsr1-fp8-mi355x-sglang, gptoss-fp4-mi355x-vllm #2

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

Closed
lishuoshuo-amd wants to merge 1 commit into from
Closed

[Hyperloom] Optimize dsr1-fp8-mi355x-sglang, gptoss-fp4-mi355x-vllm #2

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
2 changes: 1 addition & 1 deletion benchmarks/single_node/dsr1_fp8_mi355x.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,7 @@ python3 -m sglang.launch_server \
--trust-remote-code \
--chunked-prefill-size 196608 \
--mem-fraction-static 0.8 --disable-radix-cache \
--num-continuous-decode-steps 4 \
--num-continuous-decode-steps 8 \
--max-prefill-tokens 196608 \
--kv-cache-dtype fp8_e4m3 \
--cuda-graph-max-bs "$CONC" $EVAL_CONTEXT_ARGS > $SERVER_LOG 2>&1 &
Expand Down
3 changes: 3 additions & 0 deletions benchmarks/single_node/gptoss_fp4_mi355x.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,6 +57,9 @@ vllm serve $MODEL --port $PORT \
--gpu-memory-utilization 0.95 \
--max-model-len $MAX_MODEL_LEN \
--block-size=64 \
--max-num-seqs 256 \
--enable-chunked-prefill \
--max-num-batched-tokens 16384 \
--no-enable-prefix-caching > $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
@@ -1,3 +1,12 @@
- config-keys:
- dsr1-fp8-mi355x-sglang
- gptoss-fp4-mi355x-vllm
description:
- 'dsr1-fp8-mi355x-sglang: --num-continuous-decode-steps: 4 → 8'
- 'gptoss-fp4-mi355x-vllm: Add --max-num-seqs 256; Add --enable-chunked-prefill
; Add --max-num-batched-tokens 16384'
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/XXX

- config-keys:
- kimik2.5-int4-mi300x-vllm
description:
Expand Down