diff --git a/docs_new/index.mdx b/docs_new/index.mdx index e0589dd2f..c254de7af 100644 --- a/docs_new/index.mdx +++ b/docs_new/index.mdx @@ -82,6 +82,61 @@ It is designed to deliver low-latency and high-throughput inference across a wid alignItems: "stretch", }} > + +
+ Bringing DeepSeek-V4 Flash RL Training to AMD Instinct MI355X GPUs with Miles +
+
+

+ {"Bringing DeepSeek-V4 Flash RL Training to AMD Instinct MI355X GPUs with Miles"} +

+

+ {"July 10, 2026"} +

+
+ + +
+ Accelerating SGLang HiCache with Netpreme X-Mem\u2122 MPU +
+
+

+ {"Accelerating SGLang HiCache with Netpreme X-Mem\u2122 MPU"} +

+

+ {"July 8, 2026"} +

+
+ - -
- Optimizing Ling-2.6-1T on TPU with SGLang-JAX: Hiding MoE Data Movement Behind Compute with One Pallas Kernel -
-
-

- {"Optimizing Ling-2.6-1T on TPU with SGLang-JAX: Hiding MoE Data Movement Behind Compute with One Pallas Kernel"} -

-

- {"June 17, 2026"} -

-
- - -
- The next generation of speculative decoding: DFlash and Spec V2 -
-
-

- {"The next generation of speculative decoding: DFlash and Spec V2"} -

-

- {"June 15, 2026"} -

-
- {/* END_LMSYS_SGLANG_BLOG_CARDS */}