ochafik/llama.cpp

Pull Requests Commits
Merge branch 'json-bounds2' into json-integ
ochafik committed 1 year ago
ca8edbeb
Merge branch 'json-type' into json-integ
ochafik committed 1 year ago
f6fd4716
Merge remote-tracking branch 'origin/master' into json-additional
ochafik committed 1 year ago
35bbac1e
reshuffle/merge min/max integ test cases
ochafik committed 1 year ago
3a80d1e1
Merge remote-tracking branch 'origin/master' into json-bounds2
ochafik committed 1 year ago
d7d957db
Merge remote-tracking branch 'origin/master' into json-type
ochafik committed 1 year ago
72282e7b
CUDA: fix MMQ writeback for int8 tensor cores (#8100)
JohannesGaessler committed 1 year ago
Verified 3b099bcd
CUDA: use MMQ instead of cuBLAS by default (#8075)
JohannesGaessler committed 1 year ago
Verified a818f302
gguf-py : fix tensor groups for encoder-decoder models in gguf-dump.py (#8090)
fairydreaming committed 1 year ago
Verified d62e4aaa
CUDA: optimize MMQ int8 tensor core performance (#8062)
JohannesGaessler committed 1 year ago
Verified 9a590c82
Option to split during conversion (#6942)
christianazinn committed 1 year ago
Verified 52fc8705
disable publishing the full-rocm docker image (#8083)
slaren committed 1 year ago
Verified 8cb508d0
embedding : more cli arguments (#7458)
YannFollet committed 1 year ago
Verified 646ef4a9
gguf-py, convert-hf : model conversion support for T5 and FLAN-T5 model variants (#5763)
fairydreaming committed 1 year ago
Verified de0d6a68
ggml : remove ggml_task_type and GGML_PERF (#8017)
slaren committed 1 year ago
Verified 95f57bb5
Merge remote-tracking branch 'origin/master' into json-bounds2
ochafik committed 1 year ago
9fb8a75e
Merge remote-tracking branch 'origin/master' into json-type
ochafik committed 1 year ago
33933b85
Merge remote-tracking branch 'origin/master' into json-additional
ochafik committed 1 year ago
65680f94
reformat grammar integ tests w/ R"""()""" strings where there's escapes
ochafik committed 1 year ago
3c64db18
update tests
ochafik committed 1 year ago
6cf4cc28
llama : add support for BitnetForCausalLM (#7931)
Eddie-Wang1120 committed 1 year ago
Verified e112b610
server : fix JSON-Scheme typo (#7975)
akx committed 1 year ago
Verified 6a2f298b
Fix typo in llama_set_embeddings comment (#8077)
danbev committed 1 year ago
Verified 11318d9a
fix CI failures (#8066)
slaren committed 1 year ago
Verified b6b9a8e6
Refactor Vulkan backend to allow multiple contexts (#7961)
0cc4m committed 1 year ago
Verified 45c0e2e4
json: nit: simplify condition
ochafik committed 1 year ago
f714d7f1
json: add integration tests for min/max bounds
ochafik committed 1 year ago
670d5a61
fix merge
ochafik committed 1 year ago
948e55e8
json: add integ. test case for additionalProperties
ochafik committed 1 year ago
5c2d3fa1
json: fix additionalProperties default, uncomment tests
ochafik committed 1 year ago
2f1a087c
Terms Of Use Privacy Policy Refund Policy Impressum