AMD Instinct

Timeline

1. Oct 7, 2026 · Research paper · 1 source
   Expert Coupling in MoE Pretraining: Reducing All-to-All Overhead with Correlated Placement and Token Shuffling
   Mixture-of-Experts (MoE) layers replace the feed-forward block of a Transformer with E expert networks, and each token is routed to k of these experts.
2. Oct 2, 2026 · Open-source release · 1 source
   sgl-project/sglang v0.5.21
   | Model | Type | Cookbook |
3. Sep 18, 2026 · Open-source release · 1 source
   sgl-project/sglang v0.5.20
   | Model | Type | PRs | Cookbook |
4. Sep 5, 2026 · Open-source release · 1 source
   sgl-project/sglang v0.5.19
   | Model | Type | PRs | Cookbook |
5. Aug 22, 2026 · Open-source release · 1 source
   sgl-project/sglang v0.5.18
   | Model | Type | PRs | Cookbook |
6. Aug 8, 2026 · Open-source release · 1 source
   sgl-project/sglang v0.5.17
   Kimi K3 day-0 support: A 2.8T-parameter multimodal LatentMoE (896 experts, top-16, routed in a 3584-dim latent space) with a 1M-token context, 69 KDA linear-attention layers interleaved with 24 MLA layers, and a MoonViT3d vision tower, shipping as a native MXFP4 checkpoint.
7. Jul 25, 2026 · Open-source release · 1 source
   sgl-project/sglang v0.5.16
   DSpark: confidence-driven speculative decoding: A new speculative algorithm.
8. Jul 10, 2026 · Open-source release · 1 source
   sgl-project/sglang v0.5.15
   GLM-5.2 NVFP4, tuned for production: We took time this cycle to tune GLM-5.2 NVFP4 on Blackwell for optimized production serving.
9. Jun 29, 2026 · Open-source release · 1 source
   vllm-project/vllm v0.24.0
   MiniMax-M3: Added support for the new MiniMax-M3 model (#45381), with a fast follow-on of BF16/FP8 indexer via MSA (#45892), MXFP4 support (#45896), FP8 sparse GQA (#45744), and extensive AMD/ROCm tuning — mxfp8 MoE/linear on gfx950 (#45725), fp8perchannel for bf16 weights on MI300X (#45854), FP8 KV-cache fix (#45720), and packed-modules mapping (#45794).
10. Jun 13, 2026 · Open-source release · 1 source
    sgl-project/sglang v0.5.13
    DeepSeek V4 — context parallelism & sparse-attention kernels: Building on the v0.5.12 Day-0 path, v0.5.13 extends DeepSeek-V4 to context-parallel serving and adds its sparse-attention kernels:

Often appears with