3131 Commits

Author SHA1 Message Date
Roy Han
907b038ff0 reduce error footprint 2024-07-15 10:57:01 -07:00
royjhan
1f73889f34
Merge branch 'royh-batchembed' into royh-embed-parallel 2024-07-12 16:44:12 -07:00
Roy Han
7e313e5964 remove redundant error check 2024-07-12 16:37:29 -07:00
Roy Han
5a8f8e96e0 clean up 2024-07-12 16:35:25 -07:00
Roy Han
7cddd6d741 parallelized 2024-07-12 16:08:12 -07:00
Roy Han
1f3aefd323 remove function closure 2024-07-12 14:45:16 -07:00
Roy Han
2d7048f410 Revert "remove function closure"
This reverts commit 55d48c6ed17abe42e7a122e69d603ef0c1506787.
2024-07-12 14:40:40 -07:00
Roy Han
55d48c6ed1 remove function closure 2024-07-12 14:35:43 -07:00
Roy Han
c0b5bf0a36 testing clean up 2024-07-12 11:45:45 -07:00
Roy Han
53e9576f46 testing clean up 2024-07-11 20:20:14 -07:00
Roy Han
dbe9527305 clean up 2024-07-11 17:28:55 -07:00
Roy Han
694388db90 set context length 2024-07-10 15:21:46 -07:00
Roy Han
cdb9fe9b06 test values 2024-07-10 09:57:36 -07:00
Roy Han
8f6d0242b6 refactoring 2024-07-09 16:19:02 -07:00
Roy Han
c697eb2a9b fix hanging on single string 2024-07-09 15:51:55 -07:00
Roy Han
b686ac144c merge conflicts 2024-07-09 14:00:13 -07:00
royjhan
786848dfd3
Merge branch 'main' into royh-batchembed 2024-07-09 13:48:06 -07:00
Roy Han
fb390b8902 embedding type 64 2024-07-09 13:41:48 -07:00
Roy Han
bcb63e6e0e touches 2024-07-09 13:37:00 -07:00
Daniel Hiltgen
9544a57ee4
Merge pull request #5579 from dhiltgen/win_static_deps
Statically link c++ and thread lib on windows
2024-07-09 12:21:13 -07:00
Daniel Hiltgen
b51e3b63ac Statically link c++ and thread lib
This makes sure we statically link the c++ and thread library on windows
to avoid unnecessary runtime dependencies on non-standard DLLs
2024-07-09 11:34:30 -07:00
Michael Yang
6bbbc50f10
Merge pull request #5440 from ollama/mxyng/messages-templates
update named templates
2024-07-09 09:36:32 -07:00
Michael Yang
9bbddc37a7
Merge pull request #5126 from ollama/mxyng/messages
update message processing
2024-07-09 09:20:44 -07:00
Jeffrey Morgan
e4ff73297d
server: fix model reloads when setting OLLAMA_NUM_PARALLEL (#5560)
* server: fix unneeded model reloads when setting `OLLAMA_NUM_PARALLEL`

* remove whitespace change

* undo some changes
v0.2.1
2024-07-08 22:32:15 -07:00
Roy Han
3342e5f035 merge conflicts 2024-07-08 15:15:09 -07:00
royjhan
b7c622dd32
Merge branch 'main' into royh-batchembed 2024-07-08 15:10:52 -07:00
Jeffrey Morgan
53da2c6965
llm: remove ambiguous comment when putting upper limit on predictions to avoid infinite generation (#5535) v0.2.0 2024-07-07 14:32:05 -04:00
Jeffrey Morgan
d8def1ff94
llm: allow gemma 2 to context shift (#5534) v0.1.49-rc14 2024-07-07 13:41:51 -04:00
Jeffrey Morgan
571dc61955
Update llama.cpp submodule to a8db2a9c (#5530) 2024-07-07 13:03:09 -04:00
Jeffrey Morgan
0e09c380fc
llm: print caching notices in debug only (#5533) 2024-07-07 12:38:04 -04:00
Jeffrey Morgan
0ee87615c7
sched: don't error if paging to disk on Windows and macOS (#5523) v0.1.49-rc13 2024-07-06 22:01:52 -04:00
Jeffrey Morgan
f8241bfba3
gpu: report system free memory instead of 0 (#5521) v0.1.49-rc12 2024-07-06 19:35:04 -04:00
Jeffrey Morgan
4607c70641
llm: add -DBUILD_SHARED_LIBS=off to common cpu cmake flags (#5520) 2024-07-06 18:58:16 -04:00
jmorganca
c12f1c5b99 release: move mingw library cleanup to correct job v0.1.49-rc11 2024-07-06 16:12:29 -04:00
jmorganca
a08f20d910 release: remove unwanted mingw dll.a files 2024-07-06 15:21:15 -04:00
jmorganca
6cea036027 Revert "llm: only statically link libstdc++"
This reverts commit 5796bfc4013f4ebe26cdbf13554332a25c405027.
2024-07-06 15:10:48 -04:00
jmorganca
5796bfc401 llm: only statically link libstdc++ v0.1.49-rc10 2024-07-06 14:06:20 -04:00
jmorganca
f1a379aa56 llm: statically link pthread and stdc++ dependencies in windows build v0.1.49-rc9 2024-07-06 12:54:02 -04:00
jmorganca
9ae146993e llm: add GGML_STATIC flag to windows static lib v0.1.49-rc8 2024-07-06 03:27:05 -04:00
Jeffrey Morgan
e0348d3fe8
llm: add COMMON_DARWIN_DEFS to arm static build (#5513) v0.1.49-rc7 2024-07-05 22:42:42 -04:00
Jeffrey Morgan
2cc854f8cb
llm: fix missing dylibs by restoring old build behavior on Linux and macOS (#5511)
* Revert "fix cmake build (#5505)"

This reverts commit 4fd5f3526a116d05cd74cfcc7217d4e6326e1bea.

* llm: fix missing dylibs by restoring old build behavior

* crlf -> lf
v0.1.49-rc6
2024-07-05 21:48:31 -04:00
Jeffrey Morgan
5304b765b2
llm: put back old include dir (#5507)
* llm: put back old include dir

* llm: update link paths for old submodule commits
2024-07-05 19:34:21 -04:00
Michael Yang
fb6cbc02fb update named templates 2024-07-05 16:29:32 -07:00
Jeffrey Morgan
4fd5f3526a
fix cmake build (#5505) v0.1.49-rc4 v0.1.49-rc5 2024-07-05 19:07:01 -04:00
Daniel Hiltgen
842f85f758
Merge pull request #5502 from dhiltgen/ci_fixes
Always go build in CI generate steps
2024-07-05 15:39:11 -07:00
Daniel Hiltgen
9d30f9f8b3 Always go build in CI generate steps
With the recent cgo changes, bugs can sneak through
if we don't make sure to `go build` all the permutations
2024-07-05 15:31:52 -07:00
Blake Mizerany
631cfd9e62
types/model: remove knowledge of digest (#5500)
This was leading to ambiguity and confusion in ollama.com, and is not
used anywhere in ollama at the moment. Once manifests are addressable by
digest, we can add this back in, and in a way that is more tailored to
the concept of addressing a manifest by digest.
2024-07-05 13:42:30 -07:00
Michael Yang
326363b3a7 no funcs 2024-07-05 13:17:25 -07:00
Michael Yang
ac7a842e55 fix model reloading
ensure runtime model changes (template, system prompt, messages,
options) are captured on model updates without needing to reload the
server
2024-07-05 13:17:25 -07:00
Michael Yang
2c3fe1fd97 comments 2024-07-05 13:17:24 -07:00