Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
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/fixed_seq_len/dsr1_fp8_mi325x.sh
Original file line number Diff line number Diff line change
Expand Up @@ -37,7 +37,7 @@ 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 \
--cuda-graph-max-bs=128 \
--cuda-graph-max-bs-decode=128 \
--chunked-prefill-size=131072 \
--num-continuous-decode-steps=4 \
--max-prefill-tokens=131072 \
Expand Down
2 changes: 1 addition & 1 deletion configs/amd-master.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -78,7 +78,7 @@ dsr1-fp8-mi300x-sglang:
- { tp: 8, conc-start: 4, conc-end: 64 }

dsr1-fp8-mi325x-sglang:
image: lmsysorg/sglang:v0.5.19-rocm700-mi30x
image: lmsysorg/sglang:v0.5.20-rocm720-mi30x
model: deepseek-ai/DeepSeek-R1-0528
model-prefix: dsr1
runner: mi325x
Expand Down
6 changes: 6 additions & 0 deletions perf-changelog.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -8455,3 +8455,9 @@
description:
- "Update B200 vLLM AgentX to DSpark6 and a new image with TP8 and DEP8 configurations."
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/3274

- config-keys:
- dsr1-fp8-mi325x-sglang
description:
- "Update SGLang image from v0.5.19-rocm700-mi30x to v0.5.20-rocm720-mi30x and rename the CUDA-graph max-bs flag."
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/3318
Loading