[DONOTMERGE] Update dpskv4 GB300 non-MTP disagg SGLang image to nightly-20260520

Author: yhyang201

.github/configs/nvidia-master.yaml

@@ -8759,7 +8759,7 @@ dsv4-fp4-gb300-dynamo-vllm:
           dp-attn: true
 
 dsv4-fp4-gb300-dynamo-sglang:
-  image: lmsysorg/sglang:nightly-dev-cu13-20260519-dbac4647
+  image: lmsysorg/sglang:nightly-dev-cu13-20260520-425dffbd
   model: deepseek-ai/DeepSeek-V4-Pro
   model-prefix: dsv4
   runner: gb300-cw

benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-gb300-10p1d-dep4-dep16-14-c8192.yaml

@@ -33,7 +33,7 @@ name: "disagg-gb300-10p1d-dep4-dep16-14-c8192"
 
 model:
   path: "deepseek-v4-pro"
-  container: "lmsysorg/sglang:nightly-dev-cu13-20260519-dbac4647"
+  container: "lmsysorg/sglang:nightly-dev-cu13-20260520-425dffbd"
   precision: "fp4"
 
 dynamo:
@@ -94,7 +94,6 @@ backend:
     SGLANG_LOG_FORWARD_ITERS: "1"
     SGLANG_LOG_MS: "1"
     SGLANG_REQUEST_STATE_WAIT_TIMEOUT: "60"
-    SGLANG_OPT_FP8_WO_A_GEMM: "0"
 
   decode_environment:
     PYTHONUNBUFFERED: "1"
@@ -119,7 +118,6 @@ backend:
     SGLANG_LOG_FORWARD_ITERS: "1"
     SGLANG_LOG_MS: "1"
     SGLANG_REQUEST_STATE_WAIT_TIMEOUT: "60"
-    SGLANG_OPT_FP8_WO_A_GEMM: "0"
     # is single-node only and corrupts results in 2-node decode setups.
 
   sglang_config:

benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-gb300-12p1d-dep4-dep12-15-c21504.yaml

@@ -33,7 +33,7 @@ name: "disagg-gb300-12p1d-dep4-dep12-15-c21504"
 
 model:
   path: "deepseek-v4-pro"
-  container: "lmsysorg/sglang:nightly-dev-cu13-20260519-dbac4647"
+  container: "lmsysorg/sglang:nightly-dev-cu13-20260520-425dffbd"
   precision: "fp4"
 
 dynamo:
@@ -94,7 +94,6 @@ backend:
     SGLANG_LOG_FORWARD_ITERS: "1"
     SGLANG_LOG_MS: "1"
     SGLANG_REQUEST_STATE_WAIT_TIMEOUT: "60"
-    SGLANG_OPT_FP8_WO_A_GEMM: "0"
 
   decode_environment:
     PYTHONUNBUFFERED: "1"
@@ -119,7 +118,6 @@ backend:
     SGLANG_LOG_FORWARD_ITERS: "1"
     SGLANG_LOG_MS: "1"
     SGLANG_REQUEST_STATE_WAIT_TIMEOUT: "60"
-    SGLANG_OPT_FP8_WO_A_GEMM: "0"
     # is single-node only and corrupts results in 2-node decode setups.
 
   sglang_config:

benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-gb300-1p1d-dep4-dep16-5-c1024.yaml

@@ -33,7 +33,7 @@ name: "disagg-gb300-1p1d-dep4-dep16-5-c1024"
 
 model:
   path: "deepseek-v4-pro"
-  container: "lmsysorg/sglang:nightly-dev-cu13-20260519-dbac4647"
+  container: "lmsysorg/sglang:nightly-dev-cu13-20260520-425dffbd"
   precision: "fp4"
 
 dynamo:
@@ -94,7 +94,6 @@ backend:
     SGLANG_LOG_FORWARD_ITERS: "1"
     SGLANG_LOG_MS: "1"
     SGLANG_REQUEST_STATE_WAIT_TIMEOUT: "60"
-    SGLANG_OPT_FP8_WO_A_GEMM: "0"
 
   decode_environment:
     PYTHONUNBUFFERED: "1"
@@ -119,7 +118,6 @@ backend:
     SGLANG_LOG_FORWARD_ITERS: "1"
     SGLANG_LOG_MS: "1"
     SGLANG_REQUEST_STATE_WAIT_TIMEOUT: "60"
-    SGLANG_OPT_FP8_WO_A_GEMM: "0"
     # is single-node only and corrupts results in 2-node decode setups.
 
   sglang_config:

benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-gb300-1p1d-tp4-tp4-2-c1.yaml

@@ -33,7 +33,7 @@ name: "disagg-gb300-1p1d-tp4-tp4-2-c1"
 
 model:
   path: "deepseek-v4-pro"
-  container: "lmsysorg/sglang:nightly-dev-cu13-20260519-dbac4647"
+  container: "lmsysorg/sglang:nightly-dev-cu13-20260520-425dffbd"
   precision: "fp4"
 
 # See ../1k1k/disagg-gb200-1p1d-dep8-tep8.yaml for the dynamo pin
@@ -93,7 +93,6 @@ backend:
     SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: "100000"
     SGLANG_DISAGGREGATION_WAITING_TIMEOUT: "100000"
     SGLANG_OPT_SWA_RELEASE_LEAF_LOCK_AFTER_WINDOW: "1"
-    SGLANG_OPT_FP8_WO_A_GEMM: "0"
 
   decode_environment:
     PYTHONUNBUFFERED: "1"
@@ -110,7 +109,6 @@ backend:
     SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: "100000"
     SGLANG_DISAGGREGATION_WAITING_TIMEOUT: "100000"
     SGLANG_OPT_SWA_RELEASE_LEAF_LOCK_AFTER_WINDOW: "1"
-    SGLANG_OPT_FP8_WO_A_GEMM: "0"
     # is single-node only and corrupts results in 2-node decode setups.
 
   sglang_config:

benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-gb300-4p1d-dep4-dep16-8-c1024.yaml

@@ -33,7 +33,7 @@ name: "disagg-gb300-4p1d-dep4-dep16-8-c1024"
 
 model:
   path: "deepseek-v4-pro"
-  container: "lmsysorg/sglang:nightly-dev-cu13-20260519-dbac4647"
+  container: "lmsysorg/sglang:nightly-dev-cu13-20260520-425dffbd"
   precision: "fp4"
 
 dynamo:
@@ -94,7 +94,6 @@ backend:
     SGLANG_LOG_FORWARD_ITERS: "1"
     SGLANG_LOG_MS: "1"
     SGLANG_REQUEST_STATE_WAIT_TIMEOUT: "60"
-    SGLANG_OPT_FP8_WO_A_GEMM: "0"
 
   decode_environment:
     PYTHONUNBUFFERED: "1"
@@ -119,7 +118,6 @@ backend:
     SGLANG_LOG_FORWARD_ITERS: "1"
     SGLANG_LOG_MS: "1"
     SGLANG_REQUEST_STATE_WAIT_TIMEOUT: "60"
-    SGLANG_OPT_FP8_WO_A_GEMM: "0"
     # is single-node only and corrupts results in 2-node decode setups.
 
   sglang_config:

benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-gb300-8p1d-dep4-dep16-12-c4096.yaml

@@ -33,7 +33,7 @@ name: "disagg-gb300-8p1d-dep4-dep16-12-c4096"
 
 model:
   path: "deepseek-v4-pro"
-  container: "lmsysorg/sglang:nightly-dev-cu13-20260519-dbac4647"
+  container: "lmsysorg/sglang:nightly-dev-cu13-20260520-425dffbd"
   precision: "fp4"
 
 dynamo:
@@ -94,7 +94,6 @@ backend:
     SGLANG_LOG_FORWARD_ITERS: "1"
     SGLANG_LOG_MS: "1"
     SGLANG_REQUEST_STATE_WAIT_TIMEOUT: "60"
-    SGLANG_OPT_FP8_WO_A_GEMM: "0"
 
   decode_environment:
     PYTHONUNBUFFERED: "1"
@@ -119,7 +118,6 @@ backend:
     SGLANG_LOG_FORWARD_ITERS: "1"
     SGLANG_LOG_MS: "1"
     SGLANG_REQUEST_STATE_WAIT_TIMEOUT: "60"
-    SGLANG_OPT_FP8_WO_A_GEMM: "0"
     # is single-node only and corrupts results in 2-node decode setups.
 
   sglang_config:

perf-changelog.yaml

@@ -3035,7 +3035,14 @@
     - "Bump ATOM image to rocm/atom:rocm7.2.3_ubuntu24.04_py3.12_pytorch_release_2.10.0_atom20260511"
     - "TP=4 shows +3.2% to +16.3% throughput improvement across 1k1k and 8k1k workloads (concurrency 4-256)"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1411
-  
+
+- config-keys:
+    - dsv4-fp4-gb300-dynamo-sglang
+  description:
+    - "Update SGLang image from nightly-dev-cu13-20260519-dbac4647 to nightly-dev-cu13-20260520-425dffbd for all non-MTP disagg configs"
+    - "Remove SGLANG_OPT_FP8_WO_A_GEMM=0 workaround (topk_v2 crash fixed upstream in sgl-project/sglang#25805)"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1528
+
 
 - config-keys:
     - qwen3.5-fp4-b300-sglang