Roy Han
|
eb7cc2d1ce
image embeddings
|
9 mesi fa |
royjhan
|
786848dfd3
Merge branch 'main' into royh-batchembed
|
9 mesi fa |
Michael Yang
|
9bbddc37a7
Merge pull request #5126 from ollama/mxyng/messages
|
9 mesi fa |
royjhan
|
b7c622dd32
Merge branch 'main' into royh-batchembed
|
9 mesi fa |
Jeffrey Morgan
|
53da2c6965
llm: remove ambiguous comment when putting upper limit on predictions to avoid infinite generation (#5535)
|
9 mesi fa |
Michael Yang
|
ac7a842e55
fix model reloading
|
10 mesi fa |
Roy Han
|
6caac01494
clear comments
|
10 mesi fa |
Roy Han
|
17de2b4405
Refactoring of legacy and new
|
10 mesi fa |
Daniel Hiltgen
|
ccd7785859
Merge pull request #5243 from dhiltgen/modelfile_use_mmap
|
10 mesi fa |
Daniel Hiltgen
|
0e982bc1f4
Fix corner cases on tmp cleaner on mac
|
10 mesi fa |
royjhan
|
a5f23d766e
Merge branch 'main' into royh-batchembed
|
10 mesi fa |
Roy Han
|
00a4cb26ca
use float32
|
10 mesi fa |
Josh Yan
|
33a65e3ba3
error
|
10 mesi fa |
Roy Han
|
aee25acb5b
move normalization to go
|
10 mesi fa |
Daniel Hiltgen
|
97c9e11768
Switch use_mmap to a pointer type
|
10 mesi fa |
Daniel Hiltgen
|
3518aaef33
Merge pull request #4218 from dhiltgen/auto_parallel
|
10 mesi fa |
Roy Han
|
c111d8bb51
normalization
|
10 mesi fa |
Roy Han
|
49e341147d
add server function
|
10 mesi fa |
Roy Han
|
c406fa7a4c
api/embed draft
|
10 mesi fa |
Roy Han
|
ff191d7cba
Initial Draft
|
10 mesi fa |
Blake Mizerany
|
cb42e607c5
llm: speed up gguf decoding by a lot (#5246)
|
10 mesi fa |
Roy Han
|
0f87628b6d
Revert "Initial Batch Embedding"
|
10 mesi fa |
Daniel Hiltgen
|
17b7186cd7
Enable concurrency by default
|
1 anno fa |
Daniel Hiltgen
|
5bf5aeec01
Refine mmap default logic on linux
|
10 mesi fa |
Daniel Hiltgen
|
96624aa412
Merge pull request #5072 from dhiltgen/windows_path
|
10 mesi fa |
Roy Han
|
c22d54895a
Initial Batch Embedding
|
10 mesi fa |
Daniel Hiltgen
|
7784ca33ce
Tighten up memory prediction logging
|
10 mesi fa |
Daniel Hiltgen
|
171796791f
Adjust mmap logic for cuda windows for faster model load
|
10 mesi fa |
Daniel Hiltgen
|
b2799f111b
Move libraries out of users path
|
10 mesi fa |
Daniel Hiltgen
|
da3bf23354
Workaround gfx900 SDMA bugs
|
11 mesi fa |