mirror of https://github.com/ollama/ollama.git
ci: place rocm windows in correct runner dir (#12487)
release.yaml #115:Commit
07e36761c3
pushed by
root
llm: Enable flash attention by default for qwen3 and qwen3moe
release.yaml #111:Commit
0bda72892c
pushed by
root
bugfix: restore the current runOptions if loading fails in the CLI (#12402)
release.yaml #110:Commit
b04e46da3e
pushed by
root
auth: fix problems with the ollama keypairs (#12373)
release.yaml #107:Commit
64883e3c4c
pushed by
root
auth: fix problems with the ollama keypairs (#12373)
release.yaml #106:Commit
64883e3c4c
pushed by
root
Merge pull request #12358 from ollama/drifkin/qwen3-coder-ampersands
release.yaml #105:Commit
3677842ff1
pushed by
root
auth: fix problems with the ollama keypairs (#12373)
release.yaml #104:Commit
64883e3c4c
pushed by
root
fix: model load for unsupported embedding models (#12311)
release.yaml #103:Commit
9f3a37fd36
pushed by
root
convert: convert bf16 vision weights to fp16 (#12324)
release.yaml #102:Commit
2717dce6fe
pushed by
root
fix: model load for unsupported embedding models (#12311)
release.yaml #101:Commit
9f3a37fd36
pushed by
root
logutil: add Trace and TraceContext helpers (#12110)
release.yaml #99:Commit
fb92b61754
pushed by
root
convert(gptoss): mxfp4 to ggml layout to avoid jit conversion (#12018)
release.yaml #98:Commit
59412fbb43
pushed by
root
readme: add Neuro SAN to community integrations (#12109)
release.yaml #97:Commit
4383a3ab7a
pushed by
root
api: implement stringer for ToolFunctionParameters (#12038)
release.yaml #96:Commit
d3450dd52e
pushed by
root
api: implement stringer for ToolFunctionParameters (#12038)
release.yaml #95:Commit
d3450dd52e
pushed by
root
api: implement stringer for ToolFunctionParameters (#12038)
release.yaml #94:Commit
d3450dd52e
pushed by
root
Revert "cuda: leverage JIT for smaller footprint (#11635)" (#11913)
release.yaml #88:Commit
d925b5350c
pushed by
root
fix arm linux build when HWCAP2_SVE2 undefined (#11908)
release.yaml #87:Commit
6eaf194b85
pushed by
root
Merge pull request #11765 from ollama/drifkin/thinking-without-content
release.yaml #84:Commit
aa9d889522
pushed by
root
server: Reduce gpt-oss context length for small VRAM GPUs
release.yaml #83:Commit
f2e9c9aff5
pushed by
root
Merge pull request #11705 from ollama/drifkin/fn-schema
release.yaml #82:Commit
2d06977ade
pushed by
root
cuda: remove compression for better compatibility (#12259)
release.yaml #77:Commit
e4ce68311a
pushed by
root
docs: fix typos and remove trailing whitespaces (#11554)
release.yaml #68:Commit
3515cc377c
pushed by
root
CONTRIBUTING: fix typo in commit message example (#11528)
release.yaml #67:Commit
b72e5adb14
pushed by
root
cmd: add default assistant role to message construction (#11431)
release.yaml #65:Commit
d73f8aa8c3
pushed by
root
docs: update modelfile.md to reflect current default num_ctx (#11189)
release.yaml #64:Commit
4261a3b0b2
pushed by
root
readme: add NativeMind to community integrations (#11242)
release.yaml #60:Commit
5d8c173529
pushed by
root
tools: fix parsing tool calls with empty arguments, missing required fields (#11233)
release.yaml #59:Commit
44b17d2bfa
pushed by
root
tools: fix parsing tool calls with empty arguments, missing required fields (#11233)
release.yaml #58:Commit
44b17d2bfa
pushed by
root
tools: fix parsing tool calls with empty arguments, missing required fields (#11233)
release.yaml #57:Commit
44b17d2bfa
pushed by
root
tools: fix parsing tool calls with empty arguments, missing required fields (#11233)
release.yaml #56:Commit
44b17d2bfa
pushed by
root
tools: fix parsing tool calls with empty arguments, missing required fields (#11233)
release.yaml #55:Commit
44b17d2bfa
pushed by
root
fs/ggml: add multiplier in graph estimates (#11208)
release.yaml #50:Commit
ba04902670
pushed by
root
tools: fix parsing tool calls without any parameters (#11101)
release.yaml #43:Commit
6bda1d2479
pushed by
root
readme: add GPTranslate to community integrations (#11071)
release.yaml #42:Commit
5a8eb0e151
pushed by
root
tools: loosen tool parsing to allow for more formats (#11030)
release.yaml #41:Commit
9f8a18ec05
pushed by
root
client: add request signing to the client (#10881)
release.yaml #34:Commit
aa25aff10d
pushed by
root
tools: relax JSON parse constraints for tool calling (#10872)
release.yaml #33:Commit
066d0f4746
pushed by
root
win: detect background upgrade in progress (#10785)
release.yaml #29:Commit
7359b02707
pushed by
root
ggml: update qwen25vl vision size estimate (#10711)
release.yaml #28:Commit
bd68d3ae50
pushed by
root
llama: allocate grammar buffer based on schema length (#10649)
release.yaml #25:Commit
ecf14a220f
pushed by
root
strip out thinking tags in message history for qwen3 & r1 (#10490)
release.yaml #21:Commit
ad3c7c9bda
pushed by
root
integration: fix embedding tests error handling (#10478)
release.yaml #20:Commit
7bec2724a5
pushed by
root
ml/backend/ggml: use default CUDA compression mode (#10314)
release.yaml #17:Commit
09bb2e30f6
pushed by
root
ml: add missing cmake property and remove additional CMakeLists.txt (#10310)
release.yaml #16:Commit
dc264be6ff
pushed by
root
Merge pull request #10290 from ollama/drifkin/template-highlighting
release.yaml #15:Commit
fbe7039618
pushed by
root
ml/backend/ggml: create a new file descriptor for tensor (#10133)
release.yaml #14:Commit
0f3f9e353d
pushed by
root
ml/backend/ggml: create a new file descriptor for tensor (#10133)
release.yaml #13:Commit
0f3f9e353d
pushed by
root
model: support for mistral-small in the ollama runner
release.yaml #12:Commit
6bd0a983cd
pushed by
root
model: fix issues with spm tokenizer for Gemma 3 (#10081)
release.yaml #11:Commit
b51e0f397c
pushed by
root
model: fix issues with spm tokenizer for Gemma 3 (#10081)
release.yaml #10:Commit
b51e0f397c
pushed by
root
docs: add molbal/orca-cli to community integrations (#9909)
release.yaml #9:Commit
e5d84fb90b
pushed by
root
docs: add molbal/orca-cli to community integrations (#9909)
release.yaml #8:Commit
e5d84fb90b
pushed by
root
Merge pull request #9897 from ollama/mxyng/chunk-load
release.yaml #7:Commit
4b34930a31
pushed by
root
server/internal/chunks: remove chunks package (#9755)
release.yaml #4:Commit
4e320b8b90
pushed by
root
Merge pull request #9703 from ollama/mxyng/gemma3-memory
release.yaml #3:Commit
4ea4d2b189
pushed by
root