ml/backend/ggml: create a new file descriptor for tensor (#10133)

improves model loading times on network-based filesystems
such as GCS fuse by creating a dedicated file descriptor for each
section of the file being read, reducing seeking

ml/backend/ggml: create a new file descriptor for tensor (#10133)

improves model loading times on network-based filesystems
such as GCS fuse by creating a dedicated file descriptor for each
section of the file being read, reducing seeking

model: support for mistral-small in the ollama runner

Mistral is a popular research lab making open source models. This updates
the forward pass of llama architecture models to support both llama models
and mistral models by accounting for additional metadata present in mistral
models, and finding the correct dimensions for the output projection.

model: fix issues with spm tokenizer for Gemma 3 (#10081)

model: fix issues with spm tokenizer for Gemma 3 (#10081)

docs: add molbal/orca-cli to community integrations (#9909)

docs: add molbal/orca-cli to community integrations (#9909)

Merge pull request #9897 from ollama/mxyng/chunk-load

ml/backend/ggml: load tensors in 128KiB chunks

Merge pull request #9824 from ollama/mxyng/sched

conditionally enable parallel pipelines

Merge pull request #9824 from ollama/mxyng/sched

conditionally enable parallel pipelines