| .. |
|
.gitignore
|
8504d2d0da
tests : .gitignore obj files
|
1 anno fa |
|
CMakeLists.txt
|
11b12de39b
llama : add llama_chat_apply_template() (#5538)
|
1 anno fa |
|
get-model.cpp
|
413e7b0559
ci : add model tests + script wrapper (#4586)
|
2 anni fa |
|
get-model.h
|
413e7b0559
ci : add model tests + script wrapper (#4586)
|
2 anni fa |
|
test-autorelease.cpp
|
f486f6e1e5
ggml : add numa options (#5377)
|
1 anno fa |
|
test-backend-ops.cpp
|
a33e6a0d2a
Adding IQ2_S and IQ2_M to complete coverage of the 2-3 bit quantization range (#5721)
|
1 anno fa |
|
test-c.c
|
fbf1ddec69
Nomic Vulkan backend (#4456)
|
1 anno fa |
|
test-chat-template.cpp
|
373ee3fbba
Add Gemma chat template (#5665)
|
1 anno fa |
|
test-double-float.cpp
|
207b51900e
ggml : move FP16 <-> FP32 code to ggml-impl.h (#3861)
|
2 anni fa |
|
test-grad0.cpp
|
5bf3953d7e
cuda : improve cuda pool efficiency using virtual memory (#4606)
|
2 anni fa |
|
test-grammar-parser.cpp
|
5d3de51f97
ggml, common, examples, tests : fixed type arguments in printf (#5528)
|
1 anno fa |
|
test-llama-grammar.cpp
|
5d3de51f97
ggml, common, examples, tests : fixed type arguments in printf (#5528)
|
1 anno fa |
|
test-model-load-cancel.cpp
|
f486f6e1e5
ggml : add numa options (#5377)
|
1 anno fa |
|
test-opt.cpp
|
ab336a9d5e
code : normalize enum names (#5697)
|
1 anno fa |
|
test-quantize-fns.cpp
|
a33e6a0d2a
Adding IQ2_S and IQ2_M to complete coverage of the 2-3 bit quantization range (#5721)
|
1 anno fa |
|
test-quantize-perf.cpp
|
a07d0fee1f
ggml : add mmla kernels for quantized GEMM (#4966)
|
1 anno fa |
|
test-rope.cpp
|
ec893798b7
llama : custom attention mask + parallel decoding + no context swaps (#3228)
|
2 anni fa |
|
test-sampling.cpp
|
26d4efd11e
sampling: fix top_k <= 0 (#5388)
|
1 anno fa |
|
test-tokenizer-0-falcon.cpp
|
f486f6e1e5
ggml : add numa options (#5377)
|
1 anno fa |
|
test-tokenizer-0-falcon.py
|
f23c0359a3
ci : add flake8 to github actions (python linting) (#4129)
|
2 anni fa |
|
test-tokenizer-0-llama.cpp
|
f486f6e1e5
ggml : add numa options (#5377)
|
1 anno fa |
|
test-tokenizer-0-llama.py
|
f23c0359a3
ci : add flake8 to github actions (python linting) (#4129)
|
2 anni fa |
|
test-tokenizer-1-bpe.cpp
|
f486f6e1e5
ggml : add numa options (#5377)
|
1 anno fa |
|
test-tokenizer-1-llama.cpp
|
f486f6e1e5
ggml : add numa options (#5377)
|
1 anno fa |
Kawrakow
a33e6a0d2a
Adding IQ2_S and IQ2_M to complete coverage of the 2-3 bit quantization range (#5721)