TitaniumtownandGitHub f8e30266d2 sycl: coalesce the ssm_conv window loads (#26612) ...

test-backend-ops perf -o SSM_CONV on an Arc Pro B70, interleaved A/B against
master, 6 reps, us/run:

  ne_a=[515,3328,1,1] ne_b=[4,3328,1,1]   n_t=512     97.68 -> 52.95   1.85x
  ne_a=[937,8192,1,1] ne_b=[4,8192,1,1]   n_t=934    516.16 -> 276.13  1.87x
  ne_a=[4,3328,1,1]   ne_b=[4,3328,1,1]   n_t=1        2.73 -> 2.71    flat

llama-bench on qwen35 27B Q4_K - Medium (48 of its 64 blocks run ssm_conv),
-ngl 99 -fa 1 -ctk f16 -ctv f16, interleaved passes of r=3:

  -b 2048 -ub 2048  pp2048  1045.1 / 1043.5 / 1043.7 -> 1069.5 / 1066.3 / 1065.9  +2.2%
  -b 2048 -ub 512   pp2048   771.8 /  772.7          ->  785.5 /  786.6           +1.8%
  -b 2048 -ub 512   tg128     23.81 /  23.88         ->   23.87 /  23.86          flat

2026-08-07 21:09:32 +03:00

..

cmake

ggml : Parallelize quant LUT init (#23595)

2026-05-25 10:15:46 +03:00

include

mtmd/ggml: add ggml_build_forward_order (#26649)

2026-08-06 00:47:59 +02:00

src

sycl: coalesce the ssm_conv window loads (#26612)

2026-08-07 21:09:32 +03:00

.gitignore

vulkan : cmake integration (#8119)

2024-07-13 18:12:39 +02:00

CMakeLists.txt

ggml : bump version to 0.19.0 (ggml/1581)

2026-08-07 17:11:25 +03:00