Godzilla v0.3.6: Laguna Architecture Support

Godzilla v0.3.6 Release Notes

• feat(models): Added Laguna architecture support (LLM_ARCH_LAGUNA) for Laguna XS.2 / M.1 GGUFs, including chat template and HF-to-GGUF conversion registration.
• Confirmed Laguna-XS-2.1-MXFP4_MOE loads and the server listens successfully. The previous load failure was missing Laguna arch support; MXFP4 CUDA kernels were already present.
• Note: Multi-platform CI package builds may be unavailable while GitHub Actions billing is locked; this release ships notes (same pattern as v0.3.5) until packaging can run again.

Godzilla v0.3.5: --kv-vram-only Support

Godzilla v0.3.5 Release Notes

• feat(kv): Added --kv-vram-only flag to force GPU KV cache allocation even when model weights are primarily in System RAM (-ngl 0/1).
• build: Rebuilt with MSVC 19.51 and CUDA 13.2 for RTX 3080 / 4090 architectures.
• compat: Full integration with VandelayNexus Hotrod Matrix optimization suite.

v0.3.3

Changelog

• Qwen 3.6 MTP Conversion Fixes: Normalized model.mtp_layer, model.mtp_layers, mtp_layer, and mtp_layers tensor prefixes to mtp. during HF-to-GGUF conversion. Registered Qwen 3.6 architectures (Qwen3_6ForConditionalGeneration, Qwen3_6ForCausalLM, Qwen3_6MoeForConditionalGeneration, and Qwen3_6MoeForCausalLM) to enable seamless, out-of-the-box conversion.
• Speculative, Quantization, and Concurrency Fixes:
  • Modified ggml-cuda/cross-ring-interleave.cu to clamp cross_len to prevent GPU buffer OOB writes, and corrected a peer-to-peer capability check.
  • Corrected block-wise quantization/dot-product logic for Q8_K64 CPU activations in ggml-iq2-bn.c.
  • Added GGML_TYPE_TURBO2_0 to token-tracking InnerQ calibration checks in set-rows.cu.
  • Resolved MSVC warning C4319 in tests/test-gguf.cpp and demoted checkpoint matching logs to LOG_DBG in prompt matching loops.
  • Dynamically scaled loop guard constraints and fixed suffix tree dangling references during alternate sequence removal.

macOS:

• macOS Apple Silicon

Linux:

• Ubuntu x64 CPU
• Ubuntu arm64 CPU
• Ubuntu x64 CUDA 12.4
• Ubuntu x64 CUDA 13.1
• Ubuntu x64 Vulkan
• Ubuntu x64 ROCm 7.2
• Ubuntu x64 SYCL

Windows:

• Windows x64 CPU
• Windows x64 SYCL
• Windows x64 CUDA 12.4 - DLLs
• Windows x64 CUDA 13.1 - DLLs
• Windows x64 HIP

Docker:

• CPU - docker pull ghcr.io/atomicmilkshake/godzilla-llama.cpp:server-cpu-v0.3.3
• CUDA - docker pull ghcr.io/atomicmilkshake/godzilla-llama.cpp:server-cuda-v0.3.3
• CUDA 12 - docker pull ghcr.io/atomicmilkshake/godzilla-llama.cpp:server-cuda12-v0.3.3
• CUDA 13 - docker pull ghcr.io/atomicmilkshake/godzilla-llama.cpp:server-cuda13-v0.3.3
• ROCm - docker pull ghcr.io/atomicmilkshake/godzilla-llama.cpp:server-rocm-v0.3.3
• Vulkan - docker pull ghcr.io/atomicmilkshake/godzilla-llama.cpp:server-vulkan-v0.3.3
• SYCL - docker pull ghcr.io/atomicmilkshake/godzilla-llama.cpp:server-sycl-v0.3.3

v0.3.2

Full Changelog: kv-god-20260629...v0.3.2