From 7e3166eca33e18e915ba80e9c89724426ff5ca23 Mon Sep 17 00:00:00 2001
From: functionstackx <47992694+functionstackx@users.noreply.github.com>
Date: Sun, 17 May 2026 19:44:41 -0400
Subject: [PATCH] Update dsv4-fp4-b300-sglang (+mtp) SGLang image to
 v0.5.12-cu130

---
 .github/configs/nvidia-master.yaml | 4 ++--
 perf-changelog.yaml                | 7 +++++++
 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/.github/configs/nvidia-master.yaml b/.github/configs/nvidia-master.yaml
index ff6386708..48fe6e6c6 100644
--- a/.github/configs/nvidia-master.yaml
+++ b/.github/configs/nvidia-master.yaml
@@ -1986,7 +1986,7 @@ dsr1-fp8-b300-sglang:
 # until a B300-specific recipe ships. Prefix caching is disabled.
 # Parallelisms and concurrency ranges mirror dsv4-fp4-b200-vllm.
 dsv4-fp4-b300-sglang:
-  image: lmsysorg/sglang:deepseek-v4-b300@sha256:2fec8d7958bb0d53b50d7bf04d6ae6a7de8a35503775826e0550a45dd8c3ee15
+  image: lmsysorg/sglang:v0.5.12-cu130
   model: deepseek-ai/DeepSeek-V4-Pro
   model-prefix: dsv4
   runner: b300
@@ -2027,7 +2027,7 @@ dsv4-fp4-b300-sglang:
   #   dp-attn: true  -> DP-attn  + flashinfer_mxfp4 + chunked-prefill 32768
   #                     + EAGLE (1,1,2) + mem-fraction 0.92 + max-running 256
 dsv4-fp4-b300-sglang-mtp:
-  image: lmsysorg/sglang:deepseek-v4-b300@sha256:26e116bd211e300dbb76924d56c5cbe6cc3ee5ee2fe314859cb8774f5bc070f3
+  image: lmsysorg/sglang:v0.5.12-cu130
   model: deepseek-ai/DeepSeek-V4-Pro
   model-prefix: dsv4
   runner: b300
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index fc763d93b..07bb3f38b 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -3022,3 +3022,10 @@
   description:
     - "Update SGLang image from nightly-dev-cu13-20260518-c67b2870 to nightly-dev-cu13-20260519-dbac4647"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1492
+
+- config-keys:
+    - dsv4-fp4-b300-sglang
+    - dsv4-fp4-b300-sglang-mtp
+  description:
+    - "Update SGLang image from SHA-pinned deepseek-v4-b300 custom build (20/18d old) to v0.5.12-cu130"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1455