ollama

Commit Graph

Author	SHA1	Message	Date
Devon Rifkin	30f8a68c4c	tools: support anyOf types afaik gpt-oss is the first model that meaningfully transforms tool function definitions in its template. We found that relatively common definitions that include `anyOf` were not working because the template was assuming that types were always defined via a `type` field. anyOf allows for fully recursive types, so I exposed a `toTypeScriptType()` function to handle this recursive logic in go and keep the templates cleaner. The gpt-oss templates will need to be updated to use this. We should keep building out our function definition support to more fully support the parts of json schema that make sense for this use case, but in the meantime this will unblock some users (e.g., zed's ollama integration w/ gpt-oss). Probably the most urgent is proper array support	8 months ago
Michael Yang	fa7776fd24	gpt-oss (#11672 ) * bf16 * tests * gpt-oss * enable gptoss for engine * rough estimate * convert to mxfp4 * handle safetensors U8 * clamp glu/linear * update tokenizer * MXFP4 support This implements the Open Compute Microscaling (MX) FP4 format as a tensor type with backend implementations focusing on mulmat and mulmatid on CPU, CUDA, and Metal. * Unit tests for MXFP4 support This exercises various operations and shapes on both CPU and GPU (if detected on the system) * cuda graph * unit test adjustments * cuda: optimize memory access Read 4 bytes at a time (8 elements) when performing mul_mat_vec_mxfp4 * mac: fix crash on old macos versions cblas_sgemm is only supported on v13.3 and up, however bf16 is only supported on v14+ so we were falling back to ggml-blas and crashing on bf16 tensors. Checking for the function being null seems to be the simplest way to condittionally avoid registering the backend. * server: Minimum context length for gptoss This model requires a minimum context length of 8192 to function effectively. Users can set higher values through all normal mechanisms but lower values will be silently reset. * ggml: Multiply by numParallel for gptoss sliding window When computing the graph size estimate, the context size is already multiplied by numParallel so estimates reflect that. However, since sliding window models use a smaller, fixed context size, they need to manually take numParallel into account. * gpt-oss integration includes harmony parser and thinking levels, etc. * fix sync * fix tests * fix lint --------- Co-authored-by: Daniel Hiltgen <daniel@ollama.com> Co-authored-by: Jesse Gross <jesse@ollama.com> Co-authored-by: Devon Rifkin <drifkin@drifkin.net>	8 months ago
Jeffrey Morgan	4f8a0166cc	tools: loosen tool argument parsing (#11509 )	8 months ago
Jeffrey Morgan	bdd9d22dfd	tools: fix parsing issue when a tool name is a substring of another (#11456 ) Co-authored-by: frob <rick+github@frob.com.au>	8 months ago
Jeffrey Morgan	44b17d2bfa	tools: fix parsing tool calls with empty arguments, missing required fields (#11233 )	9 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	9f8a18ec05	tools: loosen tool parsing to allow for more formats (#11030 )	10 months ago
Parth Sareen	65f10c2823	tools: resiliency upgrade to name and arg extraction from template (#10917 )	10 months ago
Parth Sareen	066d0f4746	tools: relax JSON parse constraints for tool calling (#10872 )	10 months ago
Parth Sareen	aea6fb9b58	tools: remove newline stripping (#10869 )	10 months ago
Parth Sareen	e8b981fa5d	tools: refactor tool call parsing and enable streaming (#10415 )	10 months ago

12 Commits (main)