b10247
ggml: use dynamic allocation for split graph inputs (#22789) ggml: use dynamic allocation for split graph inputs Replace fixed-size GGML_SCHED_MAX_SPLIT_INPUTS arrays with dynamically allocated buffers in…
Latest
b10246
opencl: route large q6_K lm_head to the flat GEMV (#26427) add a direct size condition for large weights; the original dimension condition is insufficient -- q6_K…
b10245
graph : fix unused input tensors in minimax m3 graph (#26519) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS…
b10244
model: M3: Move MSA into a new memory implementation (#26338) Move MSA logic from llama-kv-cache into llama-kv-cache-msa cont : minor cont : ws fix Co-authored-by: Georgi…
b10243
llama : allocate indexer cache only in "full" indexer layers (#26474) Co-authored-by: Stanisław Szymczyk sszymczy@gmail.com Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64,…
b10242
CUDA: Add backend sampler for penalties sampler (#25262) sampling: enhance penalty handling in common_sampler_init Set default value for penalty_last_n based on model context if not specified.…
b10241
CUDA: Fix data-races when reusing SMEM in block_reduce (#26385) CUDA: Fix data-races when reusing block_reduce block_reduce currently doesn't resync after reading from SMEM, causing potential data-races…
b10240
server: add notice for upcoming default port change 8080 --> 9931 (#26508) server: add notice for upcoming default port change 8080 --> 6631 add link to…
b10238
model: MTP support for Qwen3-Next (#25589) mtp for qwen3nex fix for python type-check Fix to compute num_mtp from directly mtp layer define opt_num_mtp_layers in _QwenMtpMixin and…
b10237
llama : MTP support for DeepSeek V3.2 (#26457) llama : MTP support for DeepSeek V3.2 model : no need to include MTP layers during DeepSeek V3.2…