b10121: ui: reduce per-token render cost when streaming (#26053)
performance harness - the empirical root Assisted-by: Claude Opus 4.8 210.36ms -> 2.67ms per streamed token Assisted-by: Claude Opus 4.8 11.58ms -> 0.62ms per streamed token…
Latest
b10107
hexagon: fix Windows crash when op_poll is enabled (#26029) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64)…
b10106
CUDA: fix external compilation of q1_0 MMQ (#25778) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS…
b10105
args: refactor mlock/mmap/directio into load-mode (#20834) args: overhaul mmap/mlock/dio into single arg Signed-off-by: Aaron Teo aaron.teo1@ibm.com docs: update docs with llama-gen-docs Signed-off-by: Aaron Teo aaron.teo1@ibm.com chore:…
b10108
hexagon: further improved pipeline of the core bits (L2, DMA, MM, FA)…
b10099
CUDA: Improve NVFP4 W4A4 activation quantization (#25730) Squash history before conflict-resolution during rebase on master WIP commit Add 32-byte loads, restore per-block amax Use nvfp4x4 intrinsic…
b10098
hexagon: activation ops update (#25974) hex-geglu: optimized all-in-one geglu microkernel hex-geglu: enable non-contiguous src and strided DMA hex-act: enable non-contiguous srs and strided DMA for rest…
b10094
common: infer the speculative type from the draft repo sidecars (#25989) With -hfd pointing to a repo that ships mtp-/dflash-/eagle3- sidecars and no --spec-type given, the…
b10093
Fix DeepSeek4 crafted template (#25414) chat: fix DS4 template to explicitly follow reference behavior Support DeepSeekv4 flag (drop_reasoning). fix: hook DS3.2 parser for DS4 as well…
b10092
ggml: enable PowerPC backend variants on AIX (#25983) ggml: enable PowerPC backend variants on AIX Allow the PowerPC CPU backend variants to be built on AIX…