 Roy Han
|
e210f8763f
merge conflicts
|
há 9 meses atrás |
 royjhan
|
3971c2333f
Merge branch 'main' into royh-precision
|
há 9 meses atrás |
 Michael Yang
|
e5c65a85df
Merge pull request #5653 from ollama/mxyng/collect-system
|
há 9 meses atrás |
 Jeffrey Morgan
|
33627331a3
app: also clean up tempdir runners on install (#5646)
|
há 9 meses atrás |
|
Michael Yang
|
36c87c433b
template: preprocess message and collect system
|
há 9 meses atrás |
|
Jeffrey Morgan
|
179737feb7
Clean up old files when installing on Windows (#5645)
|
há 9 meses atrás |
|
Michael Yang
|
47353f5ee4
Merge pull request #5639 from ollama/mxyng/unaggregated-system
|
há 9 meses atrás |
 Josh
|
10e768826c
fix: quant err message (#5616)
|
há 9 meses atrás |
|
Michael Yang
|
5056bb9c01
rename aggregate to contents
|
há 9 meses atrás |
|
Jeffrey Morgan
|
c4cf8ad559
llm: avoid loading model if system memory is too small (#5637)
|
há 9 meses atrás |
|
Michael Yang
|
57ec6901eb
revert embedded templates to use prompt/response
|
há 9 meses atrás |
|
Michael Yang
|
e64f9ebb44
do no automatically aggregate system messages
|
há 9 meses atrás |
|
Jeffrey Morgan
|
791650ddef
sched: only error when over-allocating system memory (#5626)
|
há 9 meses atrás |
|
Jeffrey Morgan
|
efbf41ed81
llm: dont link cuda with compat libs (#5621)
|
há 9 meses atrás |
|
Michael Yang
|
cf15589851
Merge pull request #5620 from ollama/mxyng/templates
|
há 9 meses atrás |
|
Michael Yang
|
19753c18c0
update embedded templates
|
há 9 meses atrás |
|
Michael Yang
|
41be28096a
add system prompt to first legacy template
|
há 9 meses atrás |
|
Michael Yang
|
37a570f962
Merge pull request #5612 from ollama/mxyng/mem
|
há 9 meses atrás |
|
Michael Yang
|
5a739ff4cb
chatglm graph
|
há 9 meses atrás |
|
Jeffrey Morgan
|
4e262eb2a8
remove `GGML_CUDA_FORCE_MMQ=on` from build (#5588)
|
há 9 meses atrás |
 Daniel Hiltgen
|
4cfcbc328f
Merge pull request #5124 from dhiltgen/amd_windows
|
há 9 meses atrás |
|
Daniel Hiltgen
|
79292ff3e0
Merge pull request #5555 from dhiltgen/msvc_deps
|
há 9 meses atrás |
|
Daniel Hiltgen
|
8ea500441d
Merge pull request #5580 from dhiltgen/cuda_overhead
|
há 9 meses atrás |
|
Daniel Hiltgen
|
b50c818623
Merge pull request #5607 from dhiltgen/win_rocm_v6
|
há 9 meses atrás |
|
Daniel Hiltgen
|
b99e750b62
Merge pull request #5605 from dhiltgen/merge_glitch
|
há 9 meses atrás |
 Daniel Hiltgen
|
1f50356e8e
Bump ROCm on windows to 6.1.2
|
há 9 meses atrás |
|
Daniel Hiltgen
|
22c81f62ec
Remove duplicate merge glitch
|
há 9 meses atrás |
|
Daniel Hiltgen
|
2d1e3c3229
Merge pull request #5503 from dhiltgen/dual_rocm
|
há 9 meses atrás |
|
royjhan
|
4918fae535
OpenAI v1/completions: allow stop token list (#5551)
|
há 9 meses atrás |
|
royjhan
|
0aff67877e
separate request tests (#5578)
|
há 9 meses atrás |
