[TEST BUILD, do not merge] Revert the cudaMemcpy2DAsync fast path from ggml-org#25057 - #151

Closed

danielhanchen wants to merge 56 commits into

revert/25057-memcpy2d-fastpath

Commits on Aug 26, 2026

conversion : fix Nemotron 3.5 Lightning layers (#27729)
danbev
authored
dac869b
ci : make cache bucket public (#27728)
CISC
authored
da9b5d6
cuda: unblock mmq for MoE on sm_60 (#26264)
dfriehs
authored
fc35562
ci: Clean up UI builds from releases (#27706)
allozaur
authored
4d19b28
rpc : implement event and async backend APIs (#18626)
rgerganov
authored
d0132a6
Implemented vulkan cross_entropy_loss and cross_entropy_loss_back (#27216)
PranavUttarkar
authored
bf94216
vulkan: warptiles currently assume warp sizes <= 64, clamp to work around larger warps (#27726)
0cc4m
authored
5e6a37c
ui: Update Dialog component styling (#27743)
allozaur
authored
0379a19
ui: Move Settings and MCP Servers routes to dialog-based views (#27744)
allozaur
authored
539f245
llama: add token ID tracking to KV cell (#27762)
ngxson
authored
925e117

Commits on Aug 27, 2026

Commits on Aug 28, 2026

tests : run test-save-load-state across all architectures (#27755)
ggerganov
authored
4e97ac8
metal : add fa-vec tunings for M4 Pro (#27824)
infinitewarp
authored
6d6b697
metal : add fa-vec tunings for M3 Max, M5 and M5 Pro (#27863)
ggerganov
authored
8963a9b
sycl: bind the f16 KV cache in place for the oneDNN SDPA path (#27468)
Titaniumtown
authored
be87620
sycl: use TILE for quantized KV decode on BMG (#26689)
johnkarlhill
authored
d077b4c
convert: prevent ndarray conversion in LazyChunkedTensor (#27869)
ngxson
authored
b19cbe9
OpenVINO: Update OV to 2026.3.1, whisper.cpp support, Qwen3.5 on NPU, and new ops (#27843)

authored
511f9c1
metal : add fa-vec tunings for M4 (#27875)
Strongtut
authored
f5e85d4
context : disable non-fused GDN and LID ops (#27877)
ggerganov
authored
8663224
Vulkan: add hoisting support for row IDs and expert count in shaders (#26686)

ravel7524
and
jeffbolznv
authored
90c26fc
ggml : fix conv_transpose_2d for multiple batches (#26132)

tekinertekin
and
ggerganov
authored
a43c398
vulkan: fix missing view-alias dependencies in ggml_vk_graph_optimize (#27812)

Eric-A-Stalee
and
jeffbolznv
authored
b387ddf
model: qwen4exp: reduce number of graph splits (#27880)
ngxson
authored
6fe7498
bench: add --tensor-read-lazy (#27881)
ngxson
authored
50f068f
snapdragon: python SDK setup (Windows) (#27903)

kurquhar
and
Kristopher Urquhart
authored
d7bd3bf

Commits on Aug 29, 2026

Commits on Aug 31, 2026

Revert the cudaMemcpy2DAsync fast path from ggml-org#25057
danielhanchen
committed
a3577d9