Skip to content
Merged
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
1 change: 1 addition & 0 deletions benchmarks/single_node/fixed_seq_len/qwen3.5_fp4_mi355x.sh
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,7 @@ if [[ "$MODEL" != /* ]]; then hf download "$MODEL"; fi
export SGLANG_USE_AITER=1
export SGLANG_USE_AITER_UNIFIED_ATTN=1
export AITER_FLYDSL_FORCE=1
export SGLANG_MAMBA_SSM_DTYPE=bfloat16
Comment thread
yichiche marked this conversation as resolved.

SERVER_LOG=/workspace/server.log
MEM_FRAC_STATIC=${MEM_FRAC_STATIC:-0.8}
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,7 @@ hf download "$MODEL"
export SGLANG_USE_AITER=1
export SGLANG_USE_AITER_UNIFIED_ATTN=1
export AITER_FLYDSL_FORCE=1
export SGLANG_MAMBA_SSM_DTYPE=bfloat16

SERVER_LOG=/workspace/server.log
MEM_FRAC_STATIC=${MEM_FRAC_STATIC:-0.8}
Expand Down
4 changes: 2 additions & 2 deletions configs/amd-master.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -470,7 +470,7 @@ qwen3.5-fp8-mi355x-sglang-disagg:
- "DECODE_MTP_SIZE=0"

qwen3.5-fp4-mi355x-sglang:
image: lmsysorg/sglang-rocm:v0.5.13-rocm720-mi35x-20260612
image: lmsysorg/sglang-rocm:v0.5.15-rocm720-mi35x-20260713
Comment thread
yichiche marked this conversation as resolved.
model: amd/Qwen3.5-397B-A17B-MXFP4
model-prefix: qwen3.5
runner: mi355x
Expand Down Expand Up @@ -512,7 +512,7 @@ qwen3.5-fp4-mi355x-atom:
- { tp: 4, conc-start: 4, conc-end: 16 }

qwen3.5-fp4-mi355x-sglang-mtp:
image: lmsysorg/sglang-rocm:v0.5.13-rocm720-mi35x-20260612
image: lmsysorg/sglang-rocm:v0.5.15-rocm720-mi35x-20260713
model: amd/Qwen3.5-397B-A17B-MXFP4
model-prefix: qwen3.5
runner: mi355x
Expand Down
9 changes: 8 additions & 1 deletion perf-changelog.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -4833,7 +4833,6 @@
- "Add GLM-5.1 FP8 GB200 disaggregated dynamo-sglang MTP config covering 8k1k, high-throughput and low-latency topologies"
- "Image: lmsysorg/sglang:v0.5.13.post1-cu130"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2123


- config-keys:
- dsv4-fp8-mi325x-vllm
Expand All @@ -4860,3 +4859,11 @@
- "Add GB300 DeepSeek-V4 dynamo-sglang agentic recipes (agg-tp4 + dep8 disagg pareto)"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2157

- config-keys:
- qwen3.5-fp4-mi355x-sglang
- qwen3.5-fp4-mi355x-sglang-mtp
description:
- "Bump image to lmsysorg/sglang-rocm:v0.5.15-rocm720-mi35x-20260713"
- "Add SGLANG_MAMBA_SSM_DTYPE=bfloat16 in both non-MTP and MTP benchmark scripts"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2201