[AMD] Add DeepSeek-R1-0528 FP8 MI355X ATOM MTP3 benchmark (#1628)

* feat(atom/dsr1-fp8-mi355x-mtp): update ATOM image to nightly_202605301523

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* chore: update perf-changelog pr-link to #1628

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Update dsr1-fp8-mi355x-atom-mtp: stable image, wider concurrency, DP-attn support

- Switch image from nightly_202605301523 to stable atom0.1.3
- Expand concurrency search space from 4-256 to 4-1024
- Refactor benchmark script to use PARALLEL_ARGS/SPEC_ARGS pattern
- Remove ISL/OSL-based max-model-len calculation
- Update perf-changelog image reference

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* dsr1_fp8_mi355x_atom_mtp.sh: remove trailing whitespace

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* perf-changelog: fix unclosed quote in dsr1-fp8-mi355x-atom-mtp entry

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* [AMD] fix dsr1-fp8-mi355x-atom-mtp: reduce concurrency limits and disable prefix caching

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: functionstackx <47992694+functionstackx@users.noreply.github.com>

Author: 3 people

.github/configs/amd-master.yaml

@@ -1197,7 +1197,7 @@ dsr1-fp8-mi355x-atom:
       - { tp: 8, conc-start: 4, conc-end: 128 }
 
 dsr1-fp8-mi355x-atom-mtp:
-  image: rocm/atom:rocm7.2.3_ubuntu24.04_py3.12_pytorch_release_2.10.0_atom20260511
+  image: rocm/atom:rocm7.2.4_ubuntu24.04_py3.12_pytorch_release_2.10.0_atom0.1.3
   model: deepseek-ai/DeepSeek-R1-0528
   model-prefix: dsr1
   runner: mi355x
@@ -1209,7 +1209,7 @@ dsr1-fp8-mi355x-atom-mtp:
     - isl: 1024
       osl: 1024
       search-space:
-      - { tp: 8, conc-start: 4, conc-end: 256, spec-decoding: mtp }
+      - { tp: 8, conc-start: 4, conc-end: 512, spec-decoding: mtp }
     - isl: 8192
       osl: 1024
       search-space:

benchmarks/single_node/fixed_seq_len/dsr1_fp8_mi355x_atom_mtp.sh

@@ -23,23 +23,22 @@ SERVER_LOG=/workspace/server.log
 
 export OMP_NUM_THREADS=1
 
-# Calculate max-model-len based on ISL and OSL
-if [ "$ISL" = "1024" ] && [ "$OSL" = "1024" ]; then
-    CALCULATED_MAX_MODEL_LEN=""
-else
-    CALCULATED_MAX_MODEL_LEN=" --max-model-len 10240 "
-fi
-
+CALCULATED_MAX_MODEL_LEN=""
 if [ "${EVAL_ONLY}" = "true" ]; then
     setup_eval_context
     CALCULATED_MAX_MODEL_LEN=" --max-model-len $EVAL_MAX_MODEL_LEN "
 fi
 
-if [ "$EP_SIZE" -gt 1 ]; then
-  EP=" --enable-expert-parallel"
-else
-  EP=" "
-fi
+PARALLEL_ARGS=(-tp "$TP") #TP
+if [ "$DP_ATTENTION" = "true" ]; then
+    if [ "$EP_SIZE" -gt 1 ]; then #DP+EP
+        PARALLEL_ARGS=(-tp "$TP" --enable-expert-parallel --enable-dp-attention )
+    else #DP+TP
+        PARALLEL_ARGS=(-tp "$TP" --enable-dp-attention )
+    fi
+fi 
+
+SPEC_ARGS=(--method mtp --num-speculative-tokens 3 )
 
 # Start GPU monitoring (power, temperature, clocks every second)
 start_gpu_monitor
@@ -49,10 +48,10 @@ set -x
 python3 -m atom.entrypoints.openai_server \
     --model $MODEL \
     --server-port $PORT \
-    -tp $TP \
-    --kv_cache_dtype fp8 $CALCULATED_MAX_MODEL_LEN $EP \
-    --method mtp \
-    --num-speculative-tokens 3 \
+    "${PARALLEL_ARGS[@]}" \
+    "${SPEC_ARGS[@]}" \
+    --kv_cache_dtype fp8 $CALCULATED_MAX_MODEL_LEN \
+    --no-enable_prefix_caching \
     > $SERVER_LOG 2>&1 &
 
 SERVER_PID=$!

perf-changelog.yaml

@@ -3360,6 +3360,14 @@
     - "Update vLLM ROCm image from nightly-4f940896a32c9e2a0eba7f50d521bf5f6b4de458 to v0.22.0"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1624
 
+- config-keys:
+    - dsr1-fp8-mi355x-atom-mtp
+  description:
+    - "Update ATOM image to rocm/atom:rocm7.2.4_ubuntu24.04_py3.12_pytorch_release_2.10.0_atom0.1.3"
+    - "isl=1024/osl=1024: +47% to +116% improvement across conc 4-256 vs prior InferenceX numbers"
+    - "isl=8192/osl=1024: +47% to +131% improvement across conc 4-256"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1628
+
 - config-keys:
     - kimik2.5-fp4-mi355x-vllm
   description: