Update NVIDIA DeepSeek sglang Docker image from v0.5.5 to v0.5.6 (#276)

* Initial plan

* Update NVIDIA DeepSeek sglang from v0.5.5 to v0.5.6

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

* make changes to perf changelog

* fix perf-change file

fix perf-changelog

* fix delete line error

* remove resource cleanup

* update perf-change logs

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: functionstackx <47992694+functionstackx@users.noreply.github.com>
Co-authored-by: Cameron Quilici <cjquilici@gmail.com>
Co-authored-by: Ankur Singh <ankusingh@nvidia.com>

Author: 4 people

.github/configs/nvidia-master.yaml

@@ -1,5 +1,5 @@
 dsr1-fp4-b200-sglang:
-  image: lmsysorg/sglang:v0.5.5-cu129-amd64
+  image: lmsysorg/sglang:v0.5.6-cu129-amd64
   model: nvidia/DeepSeek-R1-0528-FP4-V2
   model-prefix: dsr1
   runner: b200
@@ -75,7 +75,7 @@ dsr1-fp4-b200-trt:
     - { tp: 8, ep: 8, dp-attn: true, conc-start: 64, conc-end: 256 }
 
 dsr1-fp8-b200-sglang:
-  image: lmsysorg/sglang:v0.5.5-cu129-amd64
+  image: lmsysorg/sglang:v0.5.6-cu129-amd64
   model: deepseek-ai/DeepSeek-R1-0528
   model-prefix: dsr1
   runner: b200
@@ -124,7 +124,7 @@ dsr1-fp8-b200-trt:
     - { tp: 8, ep: 8, conc-start: 4, conc-end: 64 }
 
 dsr1-fp8-h200-sglang:
-  image: lmsysorg/sglang:v0.5.5-cu129-amd64
+  image: lmsysorg/sglang:v0.5.6-cu129-amd64
   model: deepseek-ai/DeepSeek-R1-0528
   model-prefix: dsr1
   runner: h200

perf-changelog.yaml

@@ -116,3 +116,11 @@
   description:
     - "Updating MI355x Deepseek-R1 FP4 SGLang Image to upstream v0.5.6.post2"
   pr-link: https://github.com/InferenceMAX/InferenceMAX/pull/369
+    
+- config-keys:
+    - dsr1-fp4-b200-sglang
+    - dsr1-fp8-b200-sglang
+    - dsr1-fp8-h200-sglang
+  description:
+    - "Update NVIDIA DeepSeek sglang Docker image from v0.5.5 to v0.5.6"
+  pr-link: https://github.com/InferenceMAX/InferenceMAX/pull/276