ochafik/llama.cpp

Pull Requests Commits

rm trailing space

ochafik committed 1 year ago

164f3af5

Update README.md

ochafik committed 1 year ago

91d0ad7c

json: revert default of additionalProperties to false

ochafik committed 1 year ago

3e367e72

json: expand ESCAPED_IN_REGEXPS_BUT_NOT_IN_LITERALS charset

ochafik committed 1 year ago

29a2d4fa

`json`: update grammars/README w/ examples & note about additionalProperties (#8132)

ochafik committed 1 year ago

Verified cb0b06a8

CI: fix release build (Ubuntu+Mac) (#8170)

loonerin committed 1 year ago

Verified 558f44bf

cmake : fix deprecated option names not working (#8171)

slaren committed 1 year ago

Verified 8172ee9d

Add chatml fallback for cpp `llama_chat_apply_template` (#8160)

ngxson committed 1 year ago

Verified 16791b8f

flake.lock: Update (#8071)

ggerganov committed 1 year ago

Verified ab367911

Control vector loading fixes (#8137)

jukofyork committed 1 year ago

Verified 97877eb1

Delete examples/llama.android/llama/CMakeLists.txt (#8165)

criminact committed 1 year ago

Verified 38795265

Add Qwen2MoE 57B-A14B model identifier (#8158)

CISC committed 1 year ago

Verified 6030c612

CUDA: fix MMQ stream-k for --split-mode row (#8167)

JohannesGaessler committed 1 year ago

Verified 85a267da

Added support for Viking pre-tokenizer (#8135)

kustaaya committed 1 year ago

Verified f675b20a

llama : fix CodeLlama FIM token checks (#8144)

CISC committed 1 year ago

Verified 911e35bb

Fix llama-android.cpp for error - "common/common.h not found" (#8145)

criminact committed 1 year ago

Verified ac146628

clip : suppress unused variable warnings (#8105)

danbev committed 1 year ago

Verified 9b31a40c

scripts : fix filename sync

ggerganov committed 1 year ago

Verified c70d117c

ci : publish new docker images only when the files change (#8142)

slaren committed 1 year ago

Verified ae5d0f4b

ggml : add GGML_CUDA_USE_GRAPHS option, restore GGML_CUDA_FORCE_CUBLAS (cmake) (#8140)

slaren committed 1 year ago

Verified 31ec3993

make : fix missing -O3 (#8143)

slaren committed 1 year ago

Verified c7ab7b61

ggerganov committed 1 year ago

Verified f2d48fff

authors : regen

ggerganov committed 1 year ago

Verified 4713bf30

devops : remove clblast + LLAMA_CUDA -> GGML_CUDA (#8139)

ggerganov committed 1 year ago

Verified 0e814dfc

readme : update API notes

ggerganov committed 1 year ago

Verified a95631ee

llama : reorganize source code + improve CMake (#8006)

ggerganov committed 1 year ago

Verified f3f65429

Clarify default MMQ for CUDA and LLAMA_CUDA_FORCE_MMQ flag (#8115)

isaac-mcfadyen committed 1 year ago

Verified 88540445

CUDA: fix misaligned shared memory read (#8123)

JohannesGaessler committed 1 year ago

Verified c8771ab5

llama : extend llm_build_ffn() to support _scale tensors (#8103)

Eddie-Wang1120 committed 1 year ago

Verified 494165f3

`json`: better support for "type" unions (e.g. nullable arrays w/ typed items) (#7863)

ochafik committed 1 year ago

Verified 9b2f16f8

Older