Skip to content

[AMD][MI35X] 0612 DSV4 #1715

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
1am9trash wants to merge 3 commits into
base: main
Choose a base branch
from
+12 −2
Open

[AMD][MI35X] 0612 DSV4 #1715

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
cbfe4b2
Update config and change log
1am9trash Jun 12, 2026
9b3c908
Update config and change log
1am9trash Jun 12, 2026
387b083
Merge branch 'main' into dsv4-mi355-sgl-0612
1am9trash Jun 12, 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
2 changes: 1 addition & 1 deletion .github/configs/amd-master.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2137,7 +2137,7 @@ dsr1-fp4-mi355x-sglang-disagg-8k1k-mtp:


dsv4-fp4-mi355x-sglang:
image: lmsysorg/sglang-rocm:v0.5.12.post1-rocm720-mi35x-20260610
image: lmsysorg/sglang-rocm:v0.5.13-rocm720-mi35x-20260612
model: deepseek-ai/DeepSeek-V4-Pro
model-prefix: dsv4
runner: mi355x
Expand Down
4 changes: 3 additions & 1 deletion benchmarks/single_node/fixed_seq_len/dsv4_fp4_mi355x_sglang.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,7 +60,9 @@ start_gpu_monitor
PARALLEL_ARGS=(
--tensor-parallel-size "$TP"
)
CHUNKED_PREFILL_SIZE=8192
if [ "${DP_ATTENTION}" = "true" ]; then
CHUNKED_PREFILL_SIZE=$((8192 * TP))
PARALLEL_ARGS+=(
--dp "$TP"
--enable-dp-attention
Expand All @@ -85,7 +87,7 @@ sglang serve \
--swa-full-tokens-ratio 0.15 \
--page-size 256 \
--context-length $MAX_MODEL_LEN \
--chunked-prefill-size 8192 \
--chunked-prefill-size $CHUNKED_PREFILL_SIZE \
--disable-shared-experts-fusion \
--tool-call-parser deepseekv4 \
--reasoning-parser deepseek-v4 \
Expand Down
8 changes: 8 additions & 0 deletions perf-changelog.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3600,6 +3600,14 @@
- "MI355x DSR1-FP4: Include TP4 configurations for 8k1k"
- "Expand the TP sweep (included TP=4) for 8k/1k configuration for conc=4 to 64"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1692

- config-keys:
- dsv4-fp4-mi355x-sglang
description:
- "Bump image to lmsysorg/sglang-rocm:v0.5.13-rocm720-mi35x-20260612."
- "Fix the intermediate_pad setting in the MoE computation in sglang PR#27858. This avoids the unnecessary overhead of computing useless padding."
- "Correct the chunk prefill setting size under tp8/dp8 config."
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1715

- config-keys:
- dsv4-fp4-gb200-dynamo-sglang
Expand Down