Jarek
02fea420e5
Add Kerlig AI, an app for macOS ( #5675 )
2024-07-13 08:33:46 -07:00
Michael Yang
22c5451fc2
fix system prompt ( #5662 )
...
* fix system prompt
* execute template when hitting previous roles
* fix tests
---------
Co-authored-by: jmorganca <jmorganca@gmail.com>
2024-07-12 21:04:44 -07:00
Michael Yang
ebc529cbb3
autodetect stop parameters from template
2024-07-12 16:01:23 -07:00
Patrick Devine
23ebbaa46e
Revert "remove template from tests"
...
This reverts commit 9ac0a7a50b
2024-07-12 15:47:17 -07:00
Patrick Devine
9ac0a7a50b
remove template from tests
2024-07-12 15:41:31 -07:00
Michael Yang
e5c65a85df
Merge pull request #5653 from ollama/mxyng/collect-system
...
template: preprocess message and collect system
2024-07-12 12:32:34 -07:00
Jeffrey Morgan
33627331a3
app: also clean up tempdir runners on install ( #5646 )
2024-07-12 12:29:23 -07:00
Michael Yang
36c87c433b
template: preprocess message and collect system
2024-07-12 12:26:43 -07:00
Jeffrey Morgan
179737feb7
Clean up old files when installing on Windows ( #5645 )
...
* app: always clean up install dir; force close applications
* remove wildcard
* revert `CloseApplications`
* whitespace
* update `LOCALAPPDATA` var
2024-07-11 22:53:46 -07:00
Michael Yang
47353f5ee4
Merge pull request #5639 from ollama/mxyng/unaggregated-system
2024-07-11 17:48:50 -07:00
Josh
10e768826c
fix: quant err message ( #5616 )
2024-07-11 17:24:29 -07:00
Michael Yang
5056bb9c01
rename aggregate to contents
2024-07-11 17:00:26 -07:00
Jeffrey Morgan
c4cf8ad559
llm: avoid loading model if system memory is too small ( #5637 )
...
* llm: avoid loading model if system memory is too small
* update log
* Instrument swap free space
On linux and windows, expose how much swap space is available
so we can take that into consideration when scheduling models
* use `systemSwapFreeMemory` in check
---------
Co-authored-by: Daniel Hiltgen <daniel@ollama.com>
2024-07-11 16:42:57 -07:00
Michael Yang
57ec6901eb
revert embedded templates to use prompt/response
...
This reverts commit 19753c18c0
2024-07-11 14:49:35 -07:00
Michael Yang
e64f9ebb44
do no automatically aggregate system messages
2024-07-11 14:49:35 -07:00
Jeffrey Morgan
791650ddef
sched: only error when over-allocating system memory ( #5626 )
2024-07-11 00:53:12 -07:00
Jeffrey Morgan
efbf41ed81
llm: dont link cuda with compat libs ( #5621 )
2024-07-10 20:01:52 -07:00
Michael Yang
cf15589851
Merge pull request #5620 from ollama/mxyng/templates
...
update embedded templates
2024-07-10 17:16:24 -07:00
Michael Yang
19753c18c0
update embedded templates
2024-07-10 17:03:08 -07:00
Michael Yang
41be28096a
add system prompt to first legacy template
2024-07-10 17:03:08 -07:00
Michael Yang
37a570f962
Merge pull request #5612 from ollama/mxyng/mem
...
chatglm graph
2024-07-10 14:18:33 -07:00
Michael Yang
5a739ff4cb
chatglm graph
2024-07-10 13:43:47 -07:00
Jeffrey Morgan
4e262eb2a8
remove GGML_CUDA_FORCE_MMQ=on from build ( #5588 )
2024-07-10 13:17:13 -07:00
Daniel Hiltgen
4cfcbc328f
Merge pull request #5124 from dhiltgen/amd_windows
...
Wire up windows AMD driver reporting
2024-07-10 12:50:23 -07:00
Daniel Hiltgen
79292ff3e0
Merge pull request #5555 from dhiltgen/msvc_deps
...
Bundle missing CRT libraries
2024-07-10 12:50:02 -07:00
Daniel Hiltgen
8ea500441d
Merge pull request #5580 from dhiltgen/cuda_overhead
...
Detect CUDA OS overhead
2024-07-10 12:47:31 -07:00
Daniel Hiltgen
b50c818623
Merge pull request #5607 from dhiltgen/win_rocm_v6
...
Bump ROCm on windows to 6.1.2
2024-07-10 12:47:10 -07:00
Daniel Hiltgen
b99e750b62
Merge pull request #5605 from dhiltgen/merge_glitch
...
Remove duplicate merge glitch
2024-07-10 11:47:08 -07:00
Daniel Hiltgen
1f50356e8e
Bump ROCm on windows to 6.1.2
...
This also adjusts our algorithm to favor our bundled ROCm.
I've confirmed VRAM reporting still doesn't work properly so we
can't yet enable concurrency by default.
2024-07-10 11:01:22 -07:00
Daniel Hiltgen
22c81f62ec
Remove duplicate merge glitch
2024-07-10 09:01:33 -07:00
Daniel Hiltgen
73e2c8f68f
Fix context exhaustion integration test for small gpus
...
On the smaller GPUs, the initial model load of llama2 took over 30s (the
default timeout for the DoGenerate helper)
2024-07-09 16:24:14 -07:00
Daniel Hiltgen
f4408219e9
Refine scheduler unit tests for reliability
...
This breaks up some of the test scenarios to create a
more reliable set of tests, as well as adding a little more
coverage.
2024-07-09 16:00:08 -07:00
Daniel Hiltgen
2d1e3c3229
Merge pull request #5503 from dhiltgen/dual_rocm
...
Workaround broken ROCm p2p copy
2024-07-09 15:44:16 -07:00
royjhan
4918fae535
OpenAI v1/completions: allow stop token list ( #5551 )
...
* stop token parsing fix
* add stop test
2024-07-09 14:01:26 -07:00
royjhan
0aff67877e
separate request tests ( #5578 )
2024-07-09 13:48:31 -07:00
Daniel Hiltgen
f6f759fc5f
Detect CUDA OS Overhead
...
This adds logic to detect skew between the driver and
management library which can be attributed to OS overhead
and records that so we can adjust subsequent management
library free VRAM updates and avoid OOM scenarios.
2024-07-09 12:21:50 -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
2024-07-08 22:32:15 -07:00
Daniel Hiltgen
b44320db13
Bundle missing CRT libraries
...
Some users are experienging runner startup errors due
to not having these msvc redist libraries on their host
2024-07-08 18:24:21 -07:00
Daniel Hiltgen
0bacb30007
Workaround broken ROCm p2p copy
...
Enable the build flag for llama.cpp to use CPU copy for multi-GPU scenarios.
2024-07-08 09:40:52 -07:00
Jeffrey Morgan
53da2c6965
llm: remove ambiguous comment when putting upper limit on predictions to avoid infinite generation ( #5535 )
2024-07-07 14:32:05 -04:00
Jeffrey Morgan
d8def1ff94
llm: allow gemma 2 to context shift ( #5534 )
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 )
2024-07-06 22:01:52 -04:00
Jeffrey Morgan
f8241bfba3
gpu: report system free memory instead of 0 ( #5521 )
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
