common: llama_load_model_from_url using --model-url #6098
common: introduce llama_load_model_from_url to download model from hf…
3221ab01
common: llama_load_model_from_url witch to libcurl dependency
a0ebdfcc
ggerganov
approved these changes
on 2024-03-16
common: PR feedback, rename the definition to LLAMA_USE_CURL
42b25dac
common: LLAMA_USE_CURL in make toolchain
7e782856
ci: compile the server with curl, add make option curl example in def…
df0d8228
llama_load_model_from_url: try to make the windows build passing
80bec989
Update Makefile
2c3a00e2
llama_load_model_from_url: typo
4135d4a5
llama_load_model_from_url: download the file only if modified based o…
5d99f322
ci: build, fix the default build to use LLAMA_CURL
921e4af9
llama_load_model_from_url: cleanup code
6633689f
phymbert
changed the title proposal: common: llama_load_model_from_url common: llama_load_model_from_url 1 year ago
Merge branch 'master' into hp/download-model-from-hf
1430e895
phymbert
changed the title common: llama_load_model_from_url common: llama_load_model_from_url using --model-url 1 year ago
ggerganov
approved these changes
on 2024-03-16
Update examples/server/README.md
e84206d1
Update common/common.cpp
4bc47b75
Update common/common.cpp
8751bd0c
Update common/common.cpp
f53bfd56
Update common/common.cpp
b0881227
Update common/common.cpp
f22456d8
Update common/common.cpp
9565ae31
Update common/common.cpp
330e28df
Update common/common.cpp
89ab37a2
Update common/common.cpp
be561a7f
Update common/common.cpp
eb9e52a2
Update examples/main/README.md
b0b49e0b
llama_load_model_from_url: fix compilation warning, clearer logging
545fef6e
server: tests: add `--model-url` tests
4fadb072
llama_load_model_from_url: coherent clearer logging
124c474b
common: CMakeLists.txt fix typo in logging when lib curl is not found
064dc076
ci: tests: windows tests add libcurl
838178a1
ngxson
commented
on 2024-03-16
ngxson
commented
on 2024-03-16
ci: tests: windows tests add libcurl
176f039a
ci: build: add libcurl in default make toolchain step
5df5605b
llama_load_model_from_url: PR feedback, use snprintf instead of strnc…
78812c6d
ci: build: add libcurl in default make toolchain step for tests
1ad5a452
ngxson
approved these changes
on 2024-03-16
slaren
commented
on 2024-03-16
common: fix windows build caused by double windows.h import
22b3bb3c
build: move the make build with env LLAMA_CURL to a dedicated place
e6848ab0
build: introduce cmake option LLAMA_CURL to trigger libcurl linking t…
d81acb68
build: move the make build with env LLAMA_CURL to a dedicated place
dbd96914
llama_load_model_from_url: minor spacing and log message changes
9da4eec0
ci: build: fix ubuntu-focal-make-curl
89d34838
ci: build: try to fix the windows build
13d8817c
common: remove old dependency to openssl
1ddaf710
common: fix build
73b4b447
common: fix windows build
a3ed3d48
common: fix windows tests
5e66ec80
common: fix windows tests
9ca4acc5
common: llama_load_model_from_url windows set CURLOPT_SSL_OPTIONS, CU…
c1b002e0
ci: tests: print server logs in case of scenario failure
cff7faac
common: llama_load_model_from_url: make it working on windows: disabl…
4fe431d4
ci: tests: increase timeout for windows
47a9e5d7
common: fix typo
31272c63
common: llama_load_model_from_url use a temporary file for downloading
f902ab6d
common: llama_load_model_from_url delete previous file before downloa…
b24f30fd
ci: tests: fix behavior on windows
fcf327f0
ggerganov
approved these changes
on 2024-03-17
phymbert
merged
d01b3c4c
into master 1 year ago
phymbert
deleted the hp/download-model-from-hf branch 1 year ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub