 royjhan
|
786848dfd3
Merge branch 'main' into royh-batchembed
|
il y a 10 mois |
 Michael Yang
|
9bbddc37a7
Merge pull request #5126 from ollama/mxyng/messages
|
il y a 10 mois |
|
royjhan
|
b7c622dd32
Merge branch 'main' into royh-batchembed
|
il y a 10 mois |
 Jeffrey Morgan
|
53da2c6965
llm: remove ambiguous comment when putting upper limit on predictions to avoid infinite generation (#5535)
|
il y a 10 mois |
|
Michael Yang
|
ac7a842e55
fix model reloading
|
il y a 10 mois |
 Roy Han
|
6caac01494
clear comments
|
il y a 10 mois |
|
Roy Han
|
17de2b4405
Refactoring of legacy and new
|
il y a 10 mois |
 Daniel Hiltgen
|
ccd7785859
Merge pull request #5243 from dhiltgen/modelfile_use_mmap
|
il y a 10 mois |
 Daniel Hiltgen
|
0e982bc1f4
Fix corner cases on tmp cleaner on mac
|
il y a 10 mois |
|
royjhan
|
a5f23d766e
Merge branch 'main' into royh-batchembed
|
il y a 10 mois |
|
Roy Han
|
00a4cb26ca
use float32
|
il y a 10 mois |
 Josh Yan
|
33a65e3ba3
error
|
il y a 10 mois |
|
Roy Han
|
aee25acb5b
move normalization to go
|
il y a 10 mois |
|
Daniel Hiltgen
|
97c9e11768
Switch use_mmap to a pointer type
|
il y a 10 mois |
|
Daniel Hiltgen
|
3518aaef33
Merge pull request #4218 from dhiltgen/auto_parallel
|
il y a 10 mois |
|
Roy Han
|
c111d8bb51
normalization
|
il y a 10 mois |
|
Roy Han
|
49e341147d
add server function
|
il y a 10 mois |
|
Roy Han
|
c406fa7a4c
api/embed draft
|
il y a 10 mois |
|
Roy Han
|
ff191d7cba
Initial Draft
|
il y a 10 mois |
 Blake Mizerany
|
cb42e607c5
llm: speed up gguf decoding by a lot (#5246)
|
il y a 10 mois |
|
Roy Han
|
0f87628b6d
Revert "Initial Batch Embedding"
|
il y a 10 mois |
|
Daniel Hiltgen
|
17b7186cd7
Enable concurrency by default
|
il y a 1 an |
|
Daniel Hiltgen
|
5bf5aeec01
Refine mmap default logic on linux
|
il y a 10 mois |
|
Daniel Hiltgen
|
96624aa412
Merge pull request #5072 from dhiltgen/windows_path
|
il y a 11 mois |
|
Roy Han
|
c22d54895a
Initial Batch Embedding
|
il y a 11 mois |
|
Daniel Hiltgen
|
7784ca33ce
Tighten up memory prediction logging
|
il y a 11 mois |
|
Daniel Hiltgen
|
171796791f
Adjust mmap logic for cuda windows for faster model load
|
il y a 11 mois |
|
Daniel Hiltgen
|
b2799f111b
Move libraries out of users path
|
il y a 11 mois |
|
Daniel Hiltgen
|
da3bf23354
Workaround gfx900 SDMA bugs
|
il y a 11 mois |
|
Daniel Hiltgen
|
6f351bf586
review comments and coverage
|
il y a 11 mois |
