ochafik/llama.cpp

Pull Requests Commits

Updating docs for eval-callback binary to use new `llama-` prefix.

HanClinto committed 2 years ago

e7e03733

add two missing llama- prefixes

ochafik committed 2 years ago

0be5f399

address gbnf-validator unused fread warning (switched to C++ / ifstream)

Olivier Chafik committed 2 years ago

f9cfd04b

rename: llama-cli-cmake-pkg(.exe)

Olivier Chafik committed 2 years ago

b8436395

fix test-eval-callback

Olivier Chafik committed 2 years ago

4881a94b

more llama-cli(.exe)

Olivier Chafik committed 2 years ago

b8cb44e8

update dockerfile refs

Olivier Chafik committed 2 years ago

051633ed

rename(make): llama-baby-llama

Olivier Chafik committed 2 years ago

1cc65144

rename dockerfile w/ llama-cli

Olivier Chafik committed 2 years ago

0fcf2c32

fix some missing -cli suffixes

Olivier Chafik committed 2 years ago

0bb2a3f2

Merge remote-tracking branch 'origin/master' into bins

Olivier Chafik committed 2 years ago

daeaeb12

rename llama|main -> llama-cli; consistent RPM bin prefixes

Olivier Chafik committed 2 years ago

5265c15d

ci : try win-2019 on server windows test (#7854)

slaren committed 2 years ago

Verified fd5ea0f8

examples : remove --instruct remnants (#7846)

ggerganov committed 2 years ago

Verified c28a8390

server : improve "prompt" handling (#7847)

ggerganov committed 2 years ago

Verified d9da0e49

CUDA: use tensor cores for MMQ (#7676)

JohannesGaessler committed 2 years ago

Verified 1f0dabda

use the correct SYCL context for host USM allocations (#7777)

bashbaug committed 2 years ago

Verified af4ae502

flake.lock: Update (#7838)

ggerganov committed 2 years ago

Verified 10ceba35

imatrix : handle partial entries (#7833)

ggerganov committed 2 years ago

Verified e95beeb1

docs: Added initial PR template with directions for doc only changes and squash merges [no ci] (#7700)

nicolasperez19 committed 2 years ago

Verified 57bf62ce

server: do not remove whitespace at the start of a completion chunk (#7830)

mgroeber9110 committed 2 years ago

Verified 3e2ee443

CUDA: revise q8_1 data layout for mul_mat_q (#7824)

JohannesGaessler committed 2 years ago

Verified 42b53d19

convert-hf : set the model name based on cli arg, if present (#7693)

sasha0552 committed 2 years ago

Verified 2decf57b

convert-hf : match model part name prefix and suffix (#7687)

compilade committed 2 years ago

Verified 5795b941

gguf-py : decouple adding metadata from writing in GGUFWriter (#7827)

compilade committed 2 years ago

Verified ed9f2521

Revert "[SYCL] Update rpc-server.cpp to include SYCL backend (#7682)" (#7808)

slaren committed 2 years ago

Verified fe1e3917

url: save -mu downloads to new cache location (#7826)

ochafik committed 2 years ago

Verified d4d915d3

rename Dockerfiles

Olivier Chafik committed 2 years ago

347f3080

gitignore /llama-*

Olivier Chafik committed 2 years ago

78eae7f3

fix llama-lookup-* Makefile rules

Olivier Chafik committed 2 years ago

efaa4412

Newer Older