# ggml v1.0.0 release

> ggml 1.0.0 drops deprecated APIs and adds FP8 support across multiple backends.
- Title: ggml v1.0.0 release · GitHub | Shortify
- Summary: ggml 1.0.0 drops deprecated APIs and adds FP8 support across multiple backends. ggml releases v1.0.0 with pruned API, FP8 support, and backend optimizations…
- Keywords: ggml, v1.0.0, cuda, metal, vulkan, fp8, moe, flashattention, backend, GitHub
- Source: GitHub — https://github.com/ggml-org/ggml/releases/tag/v1.0.0
- Read time: 1 min
- Topics: ggml, v1.0.0, cuda, metal, vulkan, fp8, moe, flashattention, backend, technology, startups
## New release
ggml 1.0.0 drops deprecated public API and legacy DIAG_MASK ops.
## API changes
Bumped RPC protocol to v9 for faster loading and graceful failure on unreachable endpoints.
## Core improvements
Scheduler skips uploading unused inputs and prefetches only inputs produced by earlier splits.
## MoE cache
MoE cache computes cache misses on CPU and copies results back asynchronously.
## Backend updates
Added few-row quantized matmuls and MoE fusion on CUDA/Metal, Vulkan prefill FlashAttention.
## CUDA enhancements
Added few-row MMQ for batch sizes 2-24 and MMVF for BF16 few-row matmuls.
## FP8 support
Added OCP FP8 support and fused NVFP4 gate/up matmuls with GLU in MMQ.
## FlashAttention
Extended FlashAttention with sm70 head-size-256 config and MMA head sizes 40/72.
## Metal improvements
Fused MoE routing and kept fusable node groups inside a single command buffer.
## Vulkan updates
Added Intel FlashAttention prefill kernel and batched tensor copies.
## SYCL changes
Added device-side MoE scheduler and cached device id to avoid VRAM overflows.
## OpenCL additions
Added decomposed Adreno FlashAttention and improved decode performance.
## Hexagon support
Added Q5_0/Q5_1 support and optimized conv_2d while adding conv_3d.
## CPU optimizations
Switched MUL_MAT to F32 src1 and accumulate FlashAttention V in F32.
## CANN updates
Fail early when a buffer type is unsupported.
## ZDNN improvements
Accept non-zdnn tensors and invalidate compute tensors after each op.
## Key takeaway

ggml releases v1.0.0 with pruned API, FP8 support, and backend optimizations for CUDA, Metal, Vulkan, and others.