 Patrick Devine
|
3c0d043b79
pass the template to the `/api/chat` endpoint
|
9 months ago |
 Daniel Hiltgen
|
4cfcbc328f
Merge pull request #5124 from dhiltgen/amd_windows
|
9 months ago |
|
Daniel Hiltgen
|
79292ff3e0
Merge pull request #5555 from dhiltgen/msvc_deps
|
9 months ago |
|
Daniel Hiltgen
|
8ea500441d
Merge pull request #5580 from dhiltgen/cuda_overhead
|
9 months ago |
|
Daniel Hiltgen
|
b50c818623
Merge pull request #5607 from dhiltgen/win_rocm_v6
|
9 months ago |
|
Daniel Hiltgen
|
b99e750b62
Merge pull request #5605 from dhiltgen/merge_glitch
|
9 months ago |
 Daniel Hiltgen
|
1f50356e8e
Bump ROCm on windows to 6.1.2
|
9 months ago |
|
Daniel Hiltgen
|
22c81f62ec
Remove duplicate merge glitch
|
9 months ago |
|
Daniel Hiltgen
|
2d1e3c3229
Merge pull request #5503 from dhiltgen/dual_rocm
|
9 months ago |
 royjhan
|
4918fae535
OpenAI v1/completions: allow stop token list (#5551)
|
9 months ago |
|
royjhan
|
0aff67877e
separate request tests (#5578)
|
9 months ago |
|
Daniel Hiltgen
|
f6f759fc5f
Detect CUDA OS Overhead
|
9 months ago |
|
Daniel Hiltgen
|
9544a57ee4
Merge pull request #5579 from dhiltgen/win_static_deps
|
9 months ago |
|
Daniel Hiltgen
|
b51e3b63ac
Statically link c++ and thread lib
|
9 months ago |
 Michael Yang
|
6bbbc50f10
Merge pull request #5440 from ollama/mxyng/messages-templates
|
9 months ago |
|
Michael Yang
|
9bbddc37a7
Merge pull request #5126 from ollama/mxyng/messages
|
9 months ago |
 Jeffrey Morgan
|
e4ff73297d
server: fix model reloads when setting `OLLAMA_NUM_PARALLEL` (#5560)
|
9 months ago |
|
Daniel Hiltgen
|
b44320db13
Bundle missing CRT libraries
|
9 months ago |
|
Daniel Hiltgen
|
0bacb30007
Workaround broken ROCm p2p copy
|
10 months ago |
|
Jeffrey Morgan
|
53da2c6965
llm: remove ambiguous comment when putting upper limit on predictions to avoid infinite generation (#5535)
|
9 months ago |
|
Jeffrey Morgan
|
d8def1ff94
llm: allow gemma 2 to context shift (#5534)
|
9 months ago |
|
Jeffrey Morgan
|
571dc61955
Update llama.cpp submodule to `a8db2a9c` (#5530)
|
9 months ago |
|
Jeffrey Morgan
|
0e09c380fc
llm: print caching notices in debug only (#5533)
|
9 months ago |
|
Jeffrey Morgan
|
0ee87615c7
sched: don't error if paging to disk on Windows and macOS (#5523)
|
9 months ago |
|
Jeffrey Morgan
|
f8241bfba3
gpu: report system free memory instead of 0 (#5521)
|
9 months ago |
|
Jeffrey Morgan
|
4607c70641
llm: add `-DBUILD_SHARED_LIBS=off` to common cpu cmake flags (#5520)
|
9 months ago |
|
jmorganca
|
c12f1c5b99
release: move mingw library cleanup to correct job
|
9 months ago |
|
jmorganca
|
a08f20d910
release: remove unwanted mingw dll.a files
|
9 months ago |
|
jmorganca
|
6cea036027
Revert "llm: only statically link libstdc++"
|
9 months ago |
|
jmorganca
|
5796bfc401
llm: only statically link libstdc++
|
9 months ago |
