tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-05 08:28:37 -04:00
Code Issues Packages Projects Releases Wiki Activity

ggml : fix quant dot product with odd number of blocks (#8549)

Browse Source 
* ggml : fix iq4_nl dot product with odd number of blocks

* ggml : fix odd blocks for ARM_NEON (#8556)

* ggml : fix iq4_nl dot product with odd number of blocks

* ggml : fix q4_1

* ggml : fix q5_0

* ggml : fix q5_1

* ggml : fix iq4_nl metal

ggml-ci

* ggml : fix q4_0

* ggml : fix q8_0

ggml-ci

* ggml : remove special Q4_0 code for first 2 blocks

* ggml : fix sumf redefinition

---------

Co-authored-by: slaren <slarengh@gmail.com>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
slaren
2024-07-19 17:17:27 +02:00
committed by GitHub
parent 57b1d4f9eb
commit 87e397d00b
4 changed files with 364 additions and 503 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-metal.m
View File

@@ -1786,10 +1786,6 @@ static enum ggml_status ggml_metal_graph_compute(
}
};
if (ggml_is_quantized(src0t)) {
GGML_ASSERT(ne00 >= nth0*nth1);
}
[encoder setComputePipelineState:pipeline];
[encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
[encoder setBuffer:id_src1 offset:offs_src1 atIndex:1];