b10269
models : fix dflash wo_a reshape on load (#26577) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64)…
Latest
b10268
ci: fix pre-built binaries no longer working on macOS 15 and below (#26375) ci: fix pre-built binaries no longer working on macOS 15 and below ci:…
b10267
speculative : refactor enabled configs common_speculative_init (#26510) This commit contains a suggestion to reduce some code duplication in common_speculative_init when adding the enabled speculative decoding configurations.…
b10265
sync : ggml Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64 (CPU)…
b10262
vulkan backend ops: implemented GATED_LINEAR_ATTN (#25601) vulkan : add GATED_LINEAR_ATTN op docs : update Vulkan ops vulkan : remove unused GLA spec constant Updated ops.md ops.md…
b10261
vocab : validate plamo2 byte tokens (#26511) validate plamo2 byte tokens --typo Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED…
b10259
model : allow reshape of tensors during load (#26531) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64)…
b10258
llama : move n_vocab from llama_sampler_data to penalty_sampler (#26520) This matches how it is done for logit_bias and mirostat samplers, see #25262 (comment) Website: https://llama.app macOS/iOS:…
b10256
sycl: parallelize the non-contiguous concat kernel (#25852) sycl: parallelize the non-contiguous concat kernel Launch geometry only: the non-contiguous concat kernel launched a single-lane work-group (1, 1,…
b10255
Extended SYCL oneDNN SDPA to non-FP16 KV caches (Q4_0–Q8_0 and FP32) (#25874) sycl: extend oneDNN SDPA to Q4_0-Q8_0 and F32 KV caches Extends the oneDNN SDPA…