Skip to content

[AMD/ROCM] ATOM DS R1 FP8 MTP 3 tokens support #984

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
seungrokj wants to merge 2 commits into
base: main
Choose a base branch
from
+9 −4
Open

[AMD/ROCM] ATOM DS R1 FP8 MTP 3 tokens support #984

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
bc90f18
ATOM ds r1 fp8 mtp 3 tokens
seungrokj Mar 31, 2026
109c974
ATOM supports DeepSeek R1 MI355X FP8 MTP 3
seungrokj Mar 31, 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: 1 addition & 2 deletions .github/configs/amd-master.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -485,12 +485,11 @@ dsr1-fp8-mi355x-atom:
- { tp: 8, conc-start: 4, conc-end: 128 }

dsr1-fp8-mi355x-atom-mtp:
image: rocm/atom:rocm7.2.0-ubuntu24.04-pytorch2.9-atom0.1.1
image: rocm/atom:rocm7.2.1-ubuntu24.04-pytorch2.9.1-atom0.1.2
model: deepseek-ai/DeepSeek-R1-0528
model-prefix: dsr1
runner: mi355x
precision: fp8
# WIP framwork (no customers yet)
framework: atom
multinode: false
seq-len-configs:
Expand Down
3 changes: 1 addition & 2 deletions benchmarks/single_node/dsr1_fp8_mi355x_atom_mtp.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,6 +53,7 @@ python3 -m atom.entrypoints.openai_server \
-tp $TP \
--kv_cache_dtype fp8 $CALCULATED_MAX_MODEL_LEN $EP \
--method mtp \
--num-speculative-tokens 3 \
> $SERVER_LOG 2>&1 &

SERVER_PID=$!
Expand Down Expand Up @@ -83,5 +84,3 @@ fi
# Stop GPU monitoring
stop_gpu_monitor
set +x

set -x
7 changes: 7 additions & 0 deletions perf-changelog.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1220,3 +1220,10 @@
- "Uses nvidia/GLM-5-NVFP4 model with modelopt_fp4 quantization"
- "Image: lmsysorg/sglang:nightly-dev-cu13-20260328-a27651d5"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/973

- config-keys:
- dsr1-fp8-mi355x-atom-mtp
description:
- "DeepSeek R1 MI355X FP8 ATOM-MTP config to support MTP 3 tokens"
- "Image: rocm/atom:rocm7.2.1-ubuntu24.04-pytorch2.9.1-atom0.1.2"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/984