Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

sycl: fuse mul_mat(gate) + mul_mat(up) + GLU for q4_K dense FFN (#26779)

Browse Source 
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%
This commit is contained in:
Titaniumtown
2026-08-14 02:26:23 -04:00
committed by GitHub
parent c6f6a92c55
commit 6509138622
8 changed files with 316 additions and 53 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/backend/SYCL.md
+1 -1
View File
@@ -804,7 +804,7 @@ User can use the device management in [docs/multi-gpu.md](https://github.com/ggm
| GGML_SYCL_ENABLE_MKL_FA | 1 (default) or 0 | Enable oneMKL GEMM flash attention for XMX-accelerated prompt processing with quantized KV cache. Automatically activates during prefill (prompt processing) when all conditions are met: (1) flash-attn enabled (`-fa` or `--flash-attn on`), (2) KV cache quantized (`--cache-type-k q8_0 --cache-type-v q8_0` or other `*_0/*_1` types), (3) batch size ≥ 1024 (`--batch-size 1024`), (4) prompt length ≥ 1024 tokens. Set to 0 to force the TILE kernel for A/B testing. Example minimum command: `llama-cli -m model.gguf -fa -ngl 99 --cache-type-k q8_0 --cache-type-v q8_0 --batch-size 1024 -p "your prompt"` |
| GGML_SYCL_MKL_FA_DEBUG | 0 (default) or 1 | Enable per-call diagnostic logging for MKL flash attention: GEMM/softmax timings, interleaved-head detection, and buffer memory usage. |
| GGML_SYCL_MKL_FA_DIAG | 0 (default) or 1 | Enable output fingerprinting for MKL flash attention. Dumps the first 64 float output values for the first 6 FA calls with n_kv ≥ 1024, labeled with kernel type (MKL/TILE/VEC) for cross-kernel comparison. |
| GGML_SYCL_ENABLE_FUSION | 0 or 1 (default) | Enable fused-kernel dispatch in graph compute (currently top-k MoE gating). |
| GGML_SYCL_ENABLE_FUSION | 0 or 1 (default) | Enable fused-kernel dispatch in graph compute. |
| GGML_SYCL_ENABLE_ESIMD | 0 or 1 (default)| Enable ESIMD kernels when available. |
| ZES_ENABLE_SYSMAN | 0 (default) or 1 | Support to get free memory of GPU by sycl::aspect::ext_intel_free_memory.<br>Recommended to use when --split-mode = layer |
| UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS | 0 (default) or 1 | Allow SYCL/Unified Runtime Level Zero device allocations larger than 4 GiB. llama.cpp's direct Level Zero allocation path requests the relaxed maximum-size limit itself when GGML_SYCL_ENABLE_LEVEL_ZERO=1. |