fix: comments and add perf-changelog.yml

Signed-off-by: simondanielsson <simon.danielsson99@hotmail.com>

Author: simondanielsson

.github/configs/amd-master.yaml

@@ -1549,7 +1549,6 @@ kimik2.5-fp4-mi355x-vllm-disagg:
           dp-attn: false
           additional-settings:
           - "PREFILL_NODES=1"
-          - "VLLM_MORIIO_CONNECTOR_READ_MODE=1"
         decode:
           num-worker: 2
           tp: 8
@@ -1570,7 +1569,6 @@ kimik2.5-fp4-mi355x-vllm-disagg:
           dp-attn: false
           additional-settings:
           - "PREFILL_NODES=1"
-          - "VLLM_MORIIO_CONNECTOR_READ_MODE=1"
         decode:
           num-worker: 2
           tp: 8
@@ -1607,7 +1605,6 @@ minimaxm2.5-fp8-mi355x-vllm-disagg:
           dp-attn: false
           additional-settings:
           - "PREFILL_NODES=1"
-          - "VLLM_MORIIO_CONNECTOR_READ_MODE=1"
         decode:
           num-worker: 2
           tp: 8
@@ -1628,7 +1625,6 @@ minimaxm2.5-fp8-mi355x-vllm-disagg:
           dp-attn: false
           additional-settings:
           - "PREFILL_NODES=1"
-          - "VLLM_MORIIO_CONNECTOR_READ_MODE=1"
         decode:
           num-worker: 2
           tp: 8

benchmarks/multi_node/amd_utils/setup_deps.sh

@@ -3,8 +3,8 @@
 # setup_deps.sh — Install missing disagg dependencies at container start.
 #
 # Dispatched by $ENGINE (set by server.sh dispatcher):
-#   vllm-disagg   -> vLLM/MoRI-IO patches + UCX/RIXL path exports
-#                    (base image: vllm/vllm-openai-rocm:v0.18.0)
+#   vllm-disagg   -> recipe deps + amd-quark + UCX/RIXL path exports
+#                    (base image: vllm/vllm-openai-rocm:nightly)
 #   sglang-disagg -> SGLang aiter gluon patch + per-model installs
 #                    (base image: lmsysorg/sglang-rocm:v0.5.12-rocm720-mi35x-*)
 #

perf-changelog.yaml

@@ -3200,3 +3200,11 @@
     - "Bump image to lmsysorg/sglang-rocm:v0.5.12.post1-rocm720-mi35x-20260523, 1P1D TP8/EP1, dp-attn false, conc [8..512]"
     - "MoRI conn.py overlay (48e459bd) via job.slurm; launcher qwen3.5_fp4_mi355x_sglang-disagg.sh"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1579
+
+- config-keys:
+    - kimik2.5-fp4-mi355x-vllm-disagg
+    - minimaxm2.5-fp8-mi355x-vllm-disagg
+  description:
+    - "Bump image to vllm/vllm-openai-rocm:nightly (MoRI-IO fixes upstreamed in vllm#40344)"
+    - "Rename a2a backend mori to mori_low_latency; set read_mode via kv_connector_extra_config instead of VLLM_MORIIO_CONNECTOR_READ_MODE env var"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1585