Ollama releases
62 articles archived · Visit source ↗ · RSS
-
Ollama releases dev-tools 10h ago
v0.31.0
launch: check for min version for hermes desktop ( #16912 )
4 -
v0.30.11
What's Changed launch: add thinking capability detection to opencode by @hoyyeva in #15434 launch: auto-install Claude Code by @hoyyeva in #16802 launch: auto-install opencode when missing by @hoyyeva in #16806 discover: fix inverted iGPU/dGPU Vulkan classification on Windows…
28 -
v0.30.11-rc1
parser/renderer: add Ornith 9B renderer/parser support ( #16920 )
23 -
v0.30.9-rc2
llm: context shift allow shiftable prompts ( #16764 )
31 -
v0.30.9-rc1
server: context shift for context windows larger than 8k, add error w…
28 -
v0.30.7
docs: update docs examples to use Gemma 4 instead of Gemma 3 ( #16607 )
7 -
v0.30.7-rc0
launch: use native Windows Hermes config path ( #16558 )
5 -
v0.30.5-rc0: llama.cpp version update (#16511)
Bump llama.cpp to b9509, which includes the upstream Gemma 4 12B multimodal projector fixes for the n_head=0 divide-by-zero crash seen on x86/CUDA/Linux/Windows. Fixes #16479 Fixes #16489 Fixes #16491 Fixes #16492 Fixes #16495
11 -
v0.30.4-rc1: llama-server: fix gemma4 patch wiring (#16477)
This will fix the "clip.cpp:4399: Unknown projector type" crash.
4 -
v0.30.4: llama-server: fix gemma4 patch wiring (#16477)
This will fix the "clip.cpp:4399: Unknown projector type" crash.
38 -
v0.30.2: fix laguna patch build breakage (#16445)
Follow up to #16396 Fix kernel template instantiation so the symbols are exported in the library.
38 -
v0.30.1: llm: ignore llama-server SSE ping comments (#16443)
llama.cpp b9478 added a default 30s SSE ping that emits colon-only comment frames (":\n\n") while streamed requests are idle; Ollama treated non-data SSE lines as JSON, so skip SSE comments in completion and chat streams.
36 -
v0.30.1-rc0
launch: isolate Codex launch configuration ( #16437 )
7 -
v0.30.0: launch: migrate Codex config (#16397)
launch: migrate Codex config
30 -
v0.30.0-rc32: llama-server followups (#16353)
llama-server followups Misc fixes for #16031 Add back dropped ROCm build flag for multi-GPU support on windows Fix amdhip64_*.dll version detection for "latest" selection Fix embeddings API for consistent normalize behavior with prior versions ci: set up for automated llama.cpp…
19 -
v0.30.0-rc28
add OLLAMA_IGPU_ENABLE and largely disable iGPUs by default
14 -
v0.30.0-rc26: Merge remote-tracking branch 'upstream/main' into llama-runner-phase-0
Conflicts: server/images.go server/images_test.go
33