diff --git a/.github/configs/nvidia-master.yaml b/.github/configs/nvidia-master.yaml
index b4084e5e4..178694a78 100644
--- a/.github/configs/nvidia-master.yaml
+++ b/.github/configs/nvidia-master.yaml
@@ -1650,7 +1650,7 @@ dsr1-fp8-b300-dynamo-trt:
         dp-attn: true
 
 dsr1-fp4-b200-sglang:
-  image: lmsysorg/sglang:v0.5.6-cu129-amd64
+  image: lmsysorg/sglang:v0.5.9-cu129-amd64
   model: nvidia/DeepSeek-R1-0528-FP4-V2
   model-prefix: dsr1
   runner: b200
@@ -1760,7 +1760,7 @@ dsr1-fp4-b200-trt-mtp:
     - { tp: 8, ep: 8, dp-attn: true, conc-start: 64, conc-end: 256, spec-decoding: mtp }
 
 dsr1-fp8-b200-sglang:
-  image: lmsysorg/sglang:v0.5.6-cu129-amd64
+  image: lmsysorg/sglang:v0.5.9-cu129-amd64
   model: deepseek-ai/DeepSeek-R1-0528
   model-prefix: dsr1
   runner: b200
@@ -1827,7 +1827,7 @@ kimik2.5-int4-b200-vllm:
     - { tp: 8, conc-start: 4, conc-end: 64 }
 
 dsr1-fp8-b200-sglang-mtp:
-  image: lmsysorg/sglang:v0.5.8-cu130-amd64
+  image: lmsysorg/sglang:v0.5.9-cu130-amd64
   model: deepseek-ai/DeepSeek-R1-0528
   model-prefix: dsr1
   runner: b200
@@ -1906,7 +1906,7 @@ dsr1-fp8-b200-trt-mtp:
     - { tp: 8, ep: 1, conc-start: 4, conc-end: 256, spec-decoding: mtp }
 
 dsr1-fp8-h200-sglang:
-  image: lmsysorg/sglang:v0.5.7-cu129-amd64
+  image: lmsysorg/sglang:v0.5.9-cu129-amd64
   model: deepseek-ai/DeepSeek-R1-0528
   model-prefix: dsr1
   runner: h200
diff --git a/benchmarks/single_node/dsr1_fp8_b200.sh b/benchmarks/single_node/dsr1_fp8_b200.sh
index 015f45f30..5d1088b5e 100644
--- a/benchmarks/single_node/dsr1_fp8_b200.sh
+++ b/benchmarks/single_node/dsr1_fp8_b200.sh
@@ -20,7 +20,7 @@ nvidia-smi
 
 hf download "$MODEL"
 
-export SGL_ENABLE_JIT_DEEPGEMM=false
+export SGLANG_ENABLE_JIT_DEEPGEMM=false
 export SGLANG_ENABLE_FLASHINFER_GEMM=true
 SERVER_LOG=/workspace/server.log
 PORT=${PORT:-8888}
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 9c4c9e438..9feb2499f 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -733,4 +733,19 @@
     - "Extend concurrency range to conc-end: 256 across all sequence lengths (1k1k, 1k8k, 8k1k)"
     - "Fix MTP 1k8k conc-start from 256 to 4 to enable full concurrency sweep"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/699
-  
+
+- config-keys:
+    - dsr1-fp4-b200-sglang
+    - dsr1-fp8-b200-sglang
+    - dsr1-fp8-b200-sglang-mtp
+    - dsr1-fp8-h200-sglang
+  description:
+    - "Update SGLang image to v0.5.9 for NVIDIA single-node DeepSeek R1 configs"
+    - "dsr1-fp4-b200-sglang: v0.5.6-cu129-amd64 → v0.5.9-cu129-amd64"
+    - "dsr1-fp8-b200-sglang: v0.5.6-cu129-amd64 → v0.5.9-cu129-amd64"
+    - "dsr1-fp8-b200-sglang-mtp: v0.5.8-cu130-amd64 → v0.5.9-cu130-amd64"
+    - "dsr1-fp8-h200-sglang: v0.5.7-cu129-amd64 → v0.5.9-cu129-amd64"
+    - "Fix deprecated SGL_ENABLE_JIT_DEEPGEMM → SGLANG_ENABLE_JIT_DEEPGEMM in dsr1_fp8_b200.sh"
+    - "SGLang 0.5.9 gains: Flashinfer 0.6.3, TRT-LLM NSA kernels for Blackwell, SpecV2 GC bug fix, MoE fused kernel optimizations"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/814
+