thonypythony
|
2c7f7ace8f
Update README.md
|
5 meses atrás |
thonypythony
|
02a0458c94
imgs
|
5 meses atrás |
Jeffrey Morgan
|
791650ddef
sched: only error when over-allocating system memory (#5626)
|
5 meses atrás |
Jeffrey Morgan
|
efbf41ed81
llm: dont link cuda with compat libs (#5621)
|
5 meses atrás |
Michael Yang
|
cf15589851
Merge pull request #5620 from ollama/mxyng/templates
|
5 meses atrás |
Michael Yang
|
19753c18c0
update embedded templates
|
5 meses atrás |
Michael Yang
|
41be28096a
add system prompt to first legacy template
|
5 meses atrás |
Michael Yang
|
37a570f962
Merge pull request #5612 from ollama/mxyng/mem
|
5 meses atrás |
Michael Yang
|
5a739ff4cb
chatglm graph
|
5 meses atrás |
Jeffrey Morgan
|
4e262eb2a8
remove `GGML_CUDA_FORCE_MMQ=on` from build (#5588)
|
5 meses atrás |
Daniel Hiltgen
|
4cfcbc328f
Merge pull request #5124 from dhiltgen/amd_windows
|
5 meses atrás |
Daniel Hiltgen
|
79292ff3e0
Merge pull request #5555 from dhiltgen/msvc_deps
|
5 meses atrás |
Daniel Hiltgen
|
8ea500441d
Merge pull request #5580 from dhiltgen/cuda_overhead
|
5 meses atrás |
Daniel Hiltgen
|
b50c818623
Merge pull request #5607 from dhiltgen/win_rocm_v6
|
5 meses atrás |
Daniel Hiltgen
|
b99e750b62
Merge pull request #5605 from dhiltgen/merge_glitch
|
5 meses atrás |
Daniel Hiltgen
|
1f50356e8e
Bump ROCm on windows to 6.1.2
|
5 meses atrás |
Daniel Hiltgen
|
22c81f62ec
Remove duplicate merge glitch
|
5 meses atrás |
Daniel Hiltgen
|
2d1e3c3229
Merge pull request #5503 from dhiltgen/dual_rocm
|
5 meses atrás |
royjhan
|
4918fae535
OpenAI v1/completions: allow stop token list (#5551)
|
5 meses atrás |
royjhan
|
0aff67877e
separate request tests (#5578)
|
5 meses atrás |
Daniel Hiltgen
|
f6f759fc5f
Detect CUDA OS Overhead
|
5 meses atrás |
Daniel Hiltgen
|
9544a57ee4
Merge pull request #5579 from dhiltgen/win_static_deps
|
5 meses atrás |
Daniel Hiltgen
|
b51e3b63ac
Statically link c++ and thread lib
|
5 meses atrás |
Michael Yang
|
6bbbc50f10
Merge pull request #5440 from ollama/mxyng/messages-templates
|
5 meses atrás |
Michael Yang
|
9bbddc37a7
Merge pull request #5126 from ollama/mxyng/messages
|
5 meses atrás |
Jeffrey Morgan
|
e4ff73297d
server: fix model reloads when setting `OLLAMA_NUM_PARALLEL` (#5560)
|
5 meses atrás |
Daniel Hiltgen
|
b44320db13
Bundle missing CRT libraries
|
5 meses atrás |
Daniel Hiltgen
|
0bacb30007
Workaround broken ROCm p2p copy
|
5 meses atrás |
Jeffrey Morgan
|
53da2c6965
llm: remove ambiguous comment when putting upper limit on predictions to avoid infinite generation (#5535)
|
5 meses atrás |
Jeffrey Morgan
|
d8def1ff94
llm: allow gemma 2 to context shift (#5534)
|
5 meses atrás |