3 Commits

Include renames

Author	SHA1	Message	Date
antirez	769a8ba42d	dspark: support exact stochastic speculative decoding	2026-08-23 15:05:13 +02:00
ivanfioravanti	bcd1e57c5e	metal: exact MXFP4 speedups for rounds 7-9 ... Integrate the MXFP4 Metal decode/prefill optimizations (rounds 7-9) as one commit. Keep both the MXFP4 half_lut/tail_cull down-pipeline selection and main's mpp_mask override for IQ2_XXS gate/up and Q2_K/IQ2_XXS down; they target disjoint quant types and coexist.	2026-08-09 11:38:00 +02:00
antirez	36ee8c1407	Add CUDA tensor parallelism and session batching	2026-07-18 18:50:03 +02:00