Update dsr1-fp8-mi325x-sglang SGLang image to v0.5.12-rocm700-mi30x (#1428)

Ref #1154

Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: Klaud Cold <Klaud-Cold@users.noreply.github.com>
Co-authored-by: claude-fix-bot <claude-fix-bot@local>
Co-authored-by: functionstackx <47992694+functionstackx@users.noreply.github.com>

Author: 4 people

.github/configs/amd-master.yaml

@@ -85,7 +85,7 @@ dsr1-fp8-mi300x-sglang:
       - { tp: 8, conc-start: 4, conc-end: 64 }
 
 dsr1-fp8-mi325x-sglang:
-  image: lmsysorg/sglang:v0.5.9-rocm700-mi30x
+  image: lmsysorg/sglang:v0.5.12-rocm700-mi30x
   model: deepseek-ai/DeepSeek-R1-0528
   model-prefix: dsr1
   runner: mi325x

perf-changelog.yaml

@@ -2653,3 +2653,10 @@
   description:
     - "Update SGLang image from v0.5.9-cu129-amd64 (74d old) to v0.5.12-cu130"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1458
+
+- config-keys:
+    - dsr1-fp8-mi325x-sglang
+  description:
+    - "Update SGLang image from v0.5.9-rocm700-mi30x to v0.5.12-rocm700-mi30x"
+    - "Workaround LlamaTokenizer.all_special_tokens_extended removal in newer transformers: prefer backend_request_func.get_tokenizer over vLLM's"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1428

utils/bench_serving/benchmark_serving.py

@@ -46,9 +46,9 @@
 from transformers import PreTrainedTokenizerBase
 
 try:
-    from vllm.transformers_utils.tokenizer import get_tokenizer
-except ImportError:
     from backend_request_func import get_tokenizer
+except ImportError:
+    from vllm.transformers_utils.tokenizer import get_tokenizer
 
 try:
     from vllm.utils import FlexibleArgumentParser