ochafik/llama.cpp

Pull Requests Commits

Update README.md

ochafik committed 2 years ago

9f7fd7da

ochafik committed 2 years ago

df1abc60

Update test-grammar-integration.cpp

ochafik committed 2 years ago

686e2b11

Update README.md

ochafik committed 2 years ago

96f9f05c

ochafik committed 2 years ago

5db02e3d

port ref + object refactor to JS

ochafik committed 2 years ago

e447fe79

simplify & fix c++ & py versions

ochafik committed 2 years ago

7c3dbda8

Update json_schema_to_grammar.py

ochafik committed 2 years ago

e4350706

port $ref change to python

ochafik committed 2 years ago

6b6ff105

Merge remote-tracking branch 'origin/master' into json-refs

ochafik committed 2 years ago

58061bed

allow mix of allOf + properties + additionalProperties

ochafik committed 2 years ago

92ead3b9

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

ochafik committed 2 years ago

Verified cb0b06a8

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

loonerin committed 2 years ago

Verified 558f44bf

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

slaren committed 2 years ago

Verified 8172ee9d

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

ngxson committed 2 years ago

Verified 16791b8f

flake.lock: Update (#8071)

ggerganov committed 2 years ago

Verified ab367911

Control vector loading fixes (#8137)

jukofyork committed 2 years ago

Verified 97877eb1

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

criminact committed 2 years ago

Verified 38795265

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

CISC committed 2 years ago

Verified 6030c612

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

JohannesGaessler committed 2 years ago

Verified 85a267da

Added support for Viking pre-tokenizer (#8135)

kustaaya committed 2 years ago

Verified f675b20a

llama : fix CodeLlama FIM token checks (#8144)

CISC committed 2 years ago

Verified 911e35bb

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

criminact committed 2 years ago

Verified ac146628

clip : suppress unused variable warnings (#8105)

danbev committed 2 years ago

Verified 9b31a40c

ochafik committed 2 years ago

629c6089

scripts : fix filename sync

ggerganov committed 2 years ago

Verified c70d117c

Update test-json-schema-to-grammar.cpp

ochafik committed 2 years ago

448bcf9d

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

slaren committed 2 years ago

Verified ae5d0f4b

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

slaren committed 2 years ago

Verified 31ec3993

make : fix missing -O3 (#8143)

slaren committed 2 years ago

Verified c7ab7b61

Older