ollama

Commit Graph

Author	SHA1	Message	Date
Devon Rifkin	a3f7dd3e98	Merge branch 'main' into drifkin/array-head-count-simple	9 months ago
Daniel Hiltgen	c85c0ebf89	CI: switch windows to vs 2022 (#11184 ) * CI: switch windows to vs 2022 * ci: fix regex match	9 months ago
Daniel Hiltgen	10a8e04a8d	avoid context overflow (#11175 ) For smaller context models, make sure we do not exceed the training size.	9 months ago
Daniel Hiltgen	1c6669e64c	Re-remove cuda v11 (#10694 ) * Re-remove cuda v11 Revert the revert - drop v11 support requiring drivers newer than Feb 23 This reverts commit `c6bcdc4223`. * Simplify layout With only one version of the GPU libraries, we can simplify things down somewhat. (Jetsons still require special handling) * distinct sbsa variant for linux arm64 This avoids accidentally trying to load the sbsa cuda libraries on a jetson system which results in crashes. * temporary prevent rocm+cuda mixed loading	9 months ago
Devon Rifkin	b2b270ad5d	Merge branch 'main' into drifkin/array-head-count-simple	9 months ago
AJ	2bb69b40c7	readme: add ai-hub to community integrations (#11169 )	9 months ago
Daniel Hiltgen	65bff664cb	build speedups (#11142 ) Enable parallel building of the GPU architectures.	9 months ago
Michael Yang	c088ac0e79	convert: utility for merging tensors (#11069 )	9 months ago
Michael Yang	0a066cfd91	Reapply "feat: incremental gguf parser (#10822 )" (#11114 ) (#11119 ) * Reapply "feat: incremental gguf parser (#10822)" (#11114) This reverts commit `a6e64fbdf2`. * fix older ggufs	9 months ago
Jesse Gross	87b7af6cee	ggml: Check return status for computation. We don't check the return status after computing the graph, which can silently lead to bad outputs if we try to keep going and future computation succeeds. This appears to happens in certain cases on Apple M2 devices. Fixes #11070	9 months ago
Daniel Hiltgen	f2527b08fb	int: add coverage for older models (#11137 ) Verified these fail on 0.9.1 and pass on HEAD.	9 months ago
Jeffrey Morgan	8bcb3125c1	benchmark: remove unused benchmark test (#11120 ) Removes a test under benchmark/ that is unused	10 months ago
Jeffrey Morgan	6baf1e31e2	Revert "Revert "ggml: Export GPU UUIDs" (#11115 )" (#11117 ) Reverts PR #11115. The original change was mistakingly reverted instead of #10822	10 months ago
Jeffrey Morgan	ed567ef43b	Revert "ggml: Export GPU UUIDs" (#11115 ) This reverts commit `aaa7818000`.	10 months ago
Jeffrey Morgan	a6e64fbdf2	Revert "feat: incremental gguf parser (#10822 )" (#11114 ) This reverts commit `6b04cad7e8`.	10 months ago
曹家巧	60cfa2a203	cache: fix comment function name in cache.go (#11110 )	10 months ago
Jeffrey Morgan	55bbf3b4a1	tools: return empty arguments object instead of null (#11113 )	10 months ago
Jeffrey Morgan	6bda1d2479	tools: fix parsing tool calls without any parameters (#11101 ) Fixes issue where tool calls that don't expect any parameters were not being parsed. This also fixes two additional issues: one where 2+ tool calls would not be correctly parsed, and cases where tool calls with invalid parameters would still get parsed	10 months ago
Jeffrey Morgan	9e125d884c	model: treat 'user defined' tokens as special tokens (#11077 )	10 months ago
Michael Yang	a6fbfc880c	gguf: fix write order (#11068 ) * ggml: test write gguf order * ggml: fix write tensor order	10 months ago
NGC13009	502028968d	readme: add ollama-launcher to community integrations (#11080 )	10 months ago
Phil	5a8eb0e151	readme: add GPTranslate to community integrations (#11071 )	10 months ago
Jeffrey Morgan	9f8a18ec05	tools: loosen tool parsing to allow for more formats (#11030 )	10 months ago
Michael Yang	6b04cad7e8	feat: incremental gguf parser (#10822 ) * incremental gguf parser * gguf: update test to not rely on gguf on disc * re-use existing create gguf * read capabilities from gguf kv * kv exists * update tests * s/doneFunc/successFunc/g * new buffered reader --------- Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>	10 months ago
Michael Yang	45f56355d5	feat: uneven splits (#11048 ) The current splitDim function only operates on tensors that are split evenly which isn't always the case, e.g. a QKV tensor. This change allows the function to be used for arbitrary splits	10 months ago
Michael Yang	0dabb4ef6a	skip tokenizer.model if possible (#11050 ) if tokenizer.json is already copied, skip tokenizer.model	10 months ago
Michael Yang	2e77aa1ae7	use nn.Linear in place of ml.Tensor (#11049 ) while nn.Linear.Forward isn't applicable for sparse MLP, it's still a nice container for the tensors	10 months ago
Attogram Project	deaabe292d	readme: add ollama-multirun to community integrations (#11038 )	10 months ago
Jeffrey Morgan	af21a5ac39	readme: update quickstart link text to Gemma 3	10 months ago
Jeffrey Morgan	f63d7f68eb	readme: update quickstart example to Gemma 3	10 months ago
Daniel Hiltgen	82ad1dbc07	mac: handle "keep" named apps (#11031 ) When a user elects to keep the existing app, the new Ollama is named `Ollama 2.app` This fixes the app startup flow to handle this naming pattern.	10 months ago
Daniel Hiltgen	feeabdadd2	spawn desktop quickly (#11011 ) Give the desktop app a hint to start fast.	10 months ago
Krzysztof Jeziorny	fc0309615e	docs: update link to AMD drivers in linux.md (#10973 )	10 months ago
Jeffrey Morgan	09d308d6b6	Revert "server: add model capabilities to the list endpoint (#10174 )" (#11004 ) This reverts commit `0943001193`.	10 months ago
Daniel Hiltgen	a8ed68bd93	launch app hidden (#10962 ) When starting the app in the background, start it hidden.	10 months ago
Daniel Hiltgen	2ae65ae471	win: handle more than 2048 processes (#10997 ) Fix an array out of bounds crash	10 months ago
Devon Rifkin	a3b6886b7d	move thinking logic into its own package (#10990 ) move thinking logic into its own package	10 months ago
Hunter Wittenborn	c6a6d7294d	docs: fix typo in development.md (#10998 )	10 months ago
Devon Rifkin	2cf007c9d1	Merge pull request #10987 from ollama/drifkin/export-thinking-parser export ThinkingParser	10 months ago
Devon Rifkin	0683efa637	export ThinkingParser	10 months ago
JasonHonKL	0943001193	server: add model capabilities to the list endpoint (#10174 )	10 months ago
HardCodeDev	5c42800fca	readme: add SimpleOllamaUnity to community integrations (#10817 )	10 months ago
Parth Sareen	65f10c2823	tools: resiliency upgrade to name and arg extraction from template (#10917 )	10 months ago
Jesse Gross	aaa7818000	ggml: Export GPU UUIDs This enables matching up devices and information reported by the backend with system management libraries such as nvml to get accurate free memory reporting.	11 months ago
Jesse Gross	f15ffc4320	llm: Make "POST predict" error message more informative "POST predict" basically means that the runner has crashed, which can have many reasons. However, many people think this is a specific error and either report only this message or group together unrelated bugs. This replaces it with a more friendly and helpful message.	11 months ago
Devon Rifkin	5f57b0ef42	add thinking support to the api and cli (#10584 ) - Both `/api/generate` and `/api/chat` now accept a `"think"` option that allows specifying whether thinking mode should be on or not - Templates get passed this new option so, e.g., qwen3's template can put `/think` or `/no_think` in the system prompt depending on the value of the setting - Models' thinking support is inferred by inspecting model templates. The prefix and suffix the parser uses to identify thinking support is also automatically inferred from templates - Thinking control & parsing is opt-in via the API to prevent breaking existing API consumers. If the `"think"` option is not specified, the behavior is unchanged from previous versions of ollama - Add parsing for thinking blocks in both streaming/non-streaming mode in both `/generate` and `/chat` - Update the CLI to make use of these changes. Users can pass `--think` or `--think=false` to control thinking, or during an interactive session they can use the commands `/set think` or `/set nothink` - A `--hidethinking` option has also been added to the CLI. This makes it easy to use thinking in scripting scenarios like `ollama run qwen3 --think --hidethinking "my question here"` where you just want to see the answer but still want the benefits of thinking models	10 months ago
Patrick Devine	aa25aff10d	client: add request signing to the client (#10881 ) If OLLAMA_AUTH is set, sign each request w/ a timestamp and pass the signature in the token header	10 months ago
Jesse Gross	ea79003180	kvcache: Skip computing causal mask for worst case graph reservation Computing an attention mask for a large context and max batch is expensive - over 100ms. Models like Gemma3 that have multiple types of caches and custom attention masks need to do this 4 times, so this adds approximately 500ms to startup time when using 128k context When we are reserving the worst case graph, we don't need the mask, only its shape, so we can skip this.	10 months ago
Kyle Steere	9239a254e0	server: abort download on empty digest Signed-off-by: Kyle Steere <kyle.steere@chainguard.dev>	10 months ago
Parth Sareen	066d0f4746	tools: relax JSON parse constraints for tool calling (#10872 )	10 months ago

1 2 3 4 5 ...

4366 Commits (a3f7dd3e98df803695f1ae165bc61a1b52142449) All Branches Search

4366 Commits (a3f7dd3e98df803695f1ae165bc61a1b52142449)

All Branches