v1.5.0

1.5.0 (2026-04-10)

Features

• compute: add AllocDeviceFloat32 and CopyToDevice to FusedEncoderProvider (8d6c90b)
• compute: add fused PatchTST encoder layer CUDA kernels (4dfd46e)

Bug Fixes

• compute: GPUEngine.Reshape honors dst argument (18a53fe)
• compute: reuse dst GPU memory instead of allocating per call (#84) (26bbd49)
• kernels: rename kernel_add in fused_encoder_bwd to avoid symbol clash (716bbd6)

v1.4.0

1.4.0 (2026-04-06)

Features

• graph: add NewPJRTClient for external PJRT usage (c8db036)
• graph: add PJRTPlan execution wrapper with KV cache state management (3e5cb40)

Bug Fixes

• ci: exclude metal and pjrt from go vet (5a7fdc3)
• kernels: update GemvQ5_0F32 test to match qhOffset/qsOffset signature (70f8fd5)

v1.3.0

1.3.0 (2026-04-03)

Features

• graph: add CompilePJRT for PJRT backend compilation (dfd77a4)
• pjrt: add buffer management (host-device transfer, readback, lifecycle) (9b5dc75)
• pjrt: add KV cache I/O rewriting and executable cache (c8decc5)
• pjrt: add PJRT C API purego bindings for plugin loading, client, and device (c675807)
• pjrt: add program execution, serialization, and full StableHLO emitter (382ea0a)
• pjrt: add StableHLO program compilation wrapper (7fcdde7)
• stablehlo: add emitter for element-wise and unary ops (499cef2)
• stablehlo: add emitter for MatMul and structural ops (13d87df)
• stablehlo: add emitter for reductions and Softmax decomposition (c07b287)
• stablehlo: add MLIR type system and SSA naming (7c68d1e)
• stablehlo: add shape inference for arithmetic ops (cac094e)
• stablehlo: add shape inference for structural ops (8bf132c)

Bug Fixes

• pjrt: centralize internal/cuda import in pjrt.go (aa8c170)
• pjrt: remove duplicate ccall/goStringN declarations (3e5fba9)

v1.2.0

1.2.0 (2026-04-01)

Features

• cuda: add Q6_K, Q5_K, Q5_0 GPU dequant kernels for M>1 prefill (d57e37e)
• cuda: add Q8 Gather kernel for GPU embedding lookup (30eb9c4)
• tensor: add QuantizeQ4K for float32 to Q4_K quantization (d0d3a82)

Bug Fixes

• compute: add Q4KStorage to UploadWeights F32 skip list (cc071b6)
• compute: CPU dequant fallback for Q4_K when K%256!=0 (f50ffa7)
• compute: use dequant+cuBLAS for Q4_K when K%256!=0 (5f21cbb)
• compute: use pool-backed GPUStorage for pool allocations (4367330)
• cuda: byte-wise loads in Q5_0 GEMV for ARM64 alignment (5f19e54)
• kernels: check null function pointer in FusedSoftmaxVMulF32 (935ad61)

Performance Improvements

• cuda: separated GPU layout for Q5_0 GEMV (d456c39)

v1.1.3

1.1.3 (2026-04-01)

Bug Fixes

• compute: add Q5_0Storage B-weight handling to CPU MatMul (e7927e5)
• compute: Q5_0 GEMV byte-wise loads for ARM64 alignment (5c7ec7a)
• compute: skip Q4Storage in UploadWeights F32 loop (revert overaggressive skip) (2e91650)
• compute: skip transpose reshape fast-path for square matrices (eab19d0)

v1.1.2

1.1.2 (2026-03-31)

Bug Fixes

• compute: upload CPU fallback MatMul results to GPU for device consistency (5bc914b)

v1.1.1

1.1.1 (2026-03-31)

Bug Fixes

• cuda: remove float4 alignment requirement from gemv_q8_kernel (1313605)
• cuda: remove float4 alignment requirement from gemv_q8_kernel (34aba3b)

v1.1.0

1.1.0 (2026-03-31)

Features

• compute: add GPUFusedSoftmaxVMul method with provider interface (d659e76)
• compute: add GPURepeatInterleave method with purego bindings (6af7b96)
• compute: add GraphCapturer interface for CUDA graph capture/replay (1f37c69)
• compute: GPU-native Copy using cudaMemcpyAsync D2D (efc8b42)
• compute: wire capture-aware pool into GPUEngine BeginCapture/EndCapture (e39b318)
• cuda: add cudaMallocAsync and cudaFreeAsync bindings (e339656)
• cuda: add cudaMemsetAsync binding and GPU-native Zero (47b5d39)
• cuda: add fused repeat-interleave kernel for GQA head expansion (91e2469)
• cuda: add fused softmax + V multiply kernel for decode attention (ef6f7ce)
• cuda: make MemPool capture-aware with SetCaptureStream (58b6337)
• gpuapi: wire FusedSoftmaxVMulF32 into KernelRunner interface (9afdb01)

Bug Fixes

• compute: copy mmap bytes to heap in mmapDevicePtr fallback (0ad23b5)
• compute: revert H2D to sync Memcpy (async breaks mmap'd tensors) (9a87e36)
• compute: use async memcpy in getDevicePtr for CUDA graph capture (b36b7ed)

v1.0.0

1.0.0 (2026-03-30)

Miscellaneous Chores

• release 1.0.0 (0230a86)

v0.15.0

0.15.0 (2026-03-29)

Features

• tensor: MmapStorage.SliceElements for zero-copy expert weight slicing (0a40e11)
• xblas: streaming GEMM for mmap'd tensors, unblocks over-RAM inference (8d80b91)