Commit Graph
3 Commits
Author SHA1 Message Date
Titaniumtown 6509138622 sycl: fuse mul_mat(gate) + mul_mat(up) + GLU for q4_K dense FFN (#26779)
Measured on Arc Pro B70 (Battlemage, Level Zero), llama-bench -r 20, two
interleaved rounds, tg128:

    qwen2.5-3B-Instruct Q4_K_M    154.18 -> 158.53 t/s   +2.8%
    gemma-2-2b-it Q4_K_M          162.45 -> 165.62 t/s   +2.0%

llama-batched-bench on qwen2.5-3B, S_TG by batch size:

      B=1   142.72 -> 147.57 t/s    +3.4%
      B=2   243.72 -> 268.26 t/s   +10.1%
      B=4   359.58 -> 398.02 t/s   +10.7%
      B=8   449.75 -> 505.63 t/s   +12.4%
2026-08-14 02:26:23 -04:00
Titaniumtown 1ee1cd9bc6 sycl: fuse UNARY(silu|sigmoid|softplus) + MUL (#26411)
Measured on Arc Pro B70 (Battlemage), Qwen3.6-27B Q4_K_M, -fa on, f16 KV,
-b 2048 -ub 2048, llama-bench -r 3, three interleaved A/B rounds:

  pp2048        1014.70 -> 1018.56 t/s   (+0.38%, within run-to-run spread)
  tg128         23.73 -> 23.86 t/s       (+0.57%)
  tg128 @ d4096 22.71 -> 22.86 t/s       (+0.62%)
2026-08-13 11:41:38 +03:00
Titaniumtown 1553725965 sycl: fuse RMS_NORM + MUL (#26015) 2026-07-31 09:17:53 +03:00