b9877
abort if we see a multi buffer (#25276) macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux:…
Latest
b9876
ggml : fix tensor-parallel + -ncmoe crash on MoE models (#25028) Tensor parallelism (-sm tensor) combined with -ncmoe (CPU-offloaded MoE experts) aborts during warm-up on MoE…
b9874
cuda : concat implementation for quantized types (#25303) cuda : concat implementation for quantized types chore : apply am17an clever suggestion to shorten the code Co-authored-by:…
b9873
llama : add guard for K/V rotation input when buffer is unallocated (#25215) llm_graph_input_attn_kv::set_input and llm_graph_input_attn_kv_iswa::set_input call set_input_k_rot / set_input_v_rot whenever the rotation tensor pointer is…
b9871
ggml : fix broken CPU concat implementation for quantized types (#25247) ggml : fix broken CPU concat implementation for quantized types tests : concat tests for…
b9870
chat: trim messages sent to StepFun parser (fixes long reasoning loops) (#25238) chat: trim messages sent to StepFun parser (fixes long reasoning loops) add regression test;…
b9867
spec: support spec-draft-p-min in DFlash (#25246) spec: support spec-draft-p-min in DFlash dflash: add n_min guard dflash: guard both n_min and n_max macOS/iOS: macOS Apple Silicon (arm64)…
b9866
cuda: enable topk-moe fusion for 288 experts (#25267) cuda: enable topk-moe fusion for 288 experts The topk-moe fusion only accepted power-of-2 expert counts (or the special-cased…
b9864
server + ui: ping silent SSE streams every 1s and kick only after 3s so slow prefill never drops healthy connections (#25241) server + ui: ping…
b9862
Remove redundant CUDA copies after gated_delta_net. (#23940) Remove redundant CUDA copies after gated_delta_net. Currently, GDN writes recurrent state snapshots into its output tail, then the graph…