Georgi Gerganov ae1bb2c8ea llama : add high-throughput mode (llama/14363) ... * kv-cache : prepare K/V buffers for separation ggml-ci * batched-bench : fix oob write ggml-ci * llama : add "virtual sequences" ggml-ci * llama : use "stream" vs "virtual sequence" ggml-ci * graph : fix stream splitting when KV cache is not used ggml-ci * kv-cache : add multi-stream save/load support ggml-ci * llama : add "--attn-streams" flag ggml-ci * kv-cache : fix handling when find_slot fails ggml-ci * kv-cache : restore find_slot impl ggml-ci * kv-cache : add comments * kv-cache : add bounds checks for sequence id ggml-ci * cont : add n_seq_max to batch allocr ggml-ci * kv-cache : perform stream copies lazily after llama_synchronize ggml-ci * kv-cache : avoid throwing exceptions across the C boundary ggml-ci * CUDA: 4D FlashAttention support (llama/14628) * CUDA: 4D FlashAttention support * CUDA: fix WMMA FA kernel * llama : rename attn_streams -> kv_unified ggml-ci * common : rename kv_split -> kv_unified ggml-ci --------- Co-authored-by: Johannes Gäßler <johannesg@5d6.de>		2025-07-20 00:23:50 +03:00
..
cmake	ggml-cpu : rework weak alias on apple targets (llama/14146)	2025-06-18 12:40:34 +03:00
include	sync : resolve conflicts (ggml/0)	2025-07-12 19:23:56 +03:00
src	llama : add high-throughput mode (llama/14363)	2025-07-20 00:23:50 +03:00
.gitignore	…
CMakeLists.txt	sync : resolve conflicts (#0)	2025-07-12 19:23:56 +03:00