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

CUDA: faster tile FA, add oob checks, more HSs (#16492)

Browse Source
This commit is contained in:
Johannes Gäßler
2025-10-11 20:54:32 +02:00
committed by GitHub
parent a3cb04744f
commit 11f0af5504
18 changed files with 1358 additions and 784 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cuda/template-instances/generate_cu_files.py
+17 -1
View File
@@ -3,8 +3,17 @@
from glob import glob
import os
HEAD_SIZES_KQ = [40, 64, 80, 96, 112, 128, 256, 576]
TYPES_KV = ["GGML_TYPE_F16", "GGML_TYPE_Q4_0", "GGML_TYPE_Q4_1", "GGML_TYPE_Q5_0", "GGML_TYPE_Q5_1", "GGML_TYPE_Q8_0"]
SOURCE_FATTN_TILE = """// This file has been autogenerated by generate_cu_files.py, do not edit manually.
#include "../fattn-tile.cuh"
DECL_FATTN_TILE_CASE({head_size_kq}, {head_size_v});
"""
SOURCE_FATTN_VEC = """// This file has been autogenerated by generate_cu_files.py, do not edit manually.
#include "../fattn-vec.cuh"
@@ -51,6 +60,11 @@ def get_short_name(long_quant_name):
for filename in glob("*.cu"):
os.remove(filename)
for head_size_kq in HEAD_SIZES_KQ:
head_size_v = head_size_kq if head_size_kq != 576 else 512
with open(f"fattn-tile-instance-dkq{head_size_kq}-dv{head_size_v}.cu", "w") as f:
f.write(SOURCE_FATTN_TILE.format(head_size_kq=head_size_kq, head_size_v=head_size_v))
for type_k in TYPES_KV:
for type_v in TYPES_KV:
with open(f"fattn-vec-instance-{get_short_name(type_k)}-{get_short_name(type_v)}.cu", "w") as f:
@@ -64,7 +78,9 @@ for ncols in [8, 16, 32, 64]:
with open(f"fattn-mma-f16-instance-ncols1_{ncols1}-ncols2_{ncols2}.cu", "w") as f:
f.write(SOURCE_FATTN_MMA_START)
for head_size_kq in [64, 80, 96, 112, 128, 256, 576]:
for head_size_kq in HEAD_SIZES_KQ:
if head_size_kq == 40:
continue
if head_size_kq != 576 and ncols2 == 16:
continue
if head_size_kq == 576 and ncols2 != 16: