Speculation used a parallel hierarchy of wrapper cache types that shadowed
the live caches and reconciled against them on commit. Replace it with
snapshot/restore on the live caches themselves: a cache snapshots itself as
a write crosses each offset, and the runner commits a batched draft by
restoring to the accepted count. The wrappers and the comparison plumbing
around them are gone.
Snapshots are lazy. A KV or rotating capture indexes into the live buffer and
owns no memory until a destructive write forces a copy-out, so rejecting a
draft is free.
Recurrent layers now validate in the same batched pass rather than falling
back to serial. A gated-delta layer reports its interior split offsets and
hands back the recurrent state at each one, which the cache records as a
snapshot.
CausalConv1D and GatedDelta now run their scan in segments cut at optional
WithSnapshotSplits offsets and return the recurrent state at each boundary
instead of just the final state. The output is identical to the unsegmented
scan; segmenting only adds a few kernel launches, not extra recurrence compute.
This lets a batched forward capture interior recurrent state without re-running
the scan, which the cache will use for speculative validation rollback points.
RecurrentCache.Put and the Qwen3.5 layer now thread the boundary-state slices,
committing the final entry as the live state.
cache.go had grown to hold every cache kind. Move KVCache (and its
speculative wrappers) to kvcache.go and RotatingKVCache (and its
sliding-window mask applier) to rotating.go, leaving cache.go with the
shared interfaces and the Speculation transaction. Pure relocation;
no behavior change.
Split the gated-delta Metal/CUDA kernels' dtype template into separate
input (InT) and state (StT) types so activations can stay in bf16/fp16
while the accumulated delta state stays in float32. Allocate the delta
state and qwen3_5's no-cache zero state in float32 to match.
This reverts commit 98e26b8c37.
The DFlash integration is too invasive to keep at this stage: it
threads DFlash-specific logic through the pipeline, base model
interfaces, and the cache layer. The recurrent cache also now
has qwen3.5 model-specific code. Revert it now and reintroduce
the self-contained, generally-useful pieces (YaRN RoPE DRY-out, draft
architecture autodetection, gated-delta fp32 state) as separate
follow-up commits.
This change adds dflash block diffusion speculative decoding to the MLX runner. Included in this change:
support for qwen3.6 moe/dense speculative decoding
draft model recurrent cache playback
RoPE/YaRN changes (DRY out the laguna/dflash MoE YaRN implementation)
support for greedy sampling / leviathan/chen sampling
This change adds support for MTP (multi-token prediction) speculative decoding for the
gemma4 model family.
It includes:
* support for importing safetensors based gemma4 draft models with `ollama create`
* a new DRAFT command in the Modelfile for specifying draft models
* a --quantize-draft flag for the ollama create command to quantize the draft model
* cache support for speculation
* changes to the rotating cache to be able to handle MTP correctly
* sampling support for draft model token prediction
---------
Co-authored-by: Daniel Hiltgen <daniel@ollama.com>
Models build their own attention masks and read K/V directly from
the cache's buffers, which ties them to the cache's storage layout.
That blocks multi-sequence batching — right-padded rows need a
query-padding mask composed onto every model — and rules out
variants like paged attention where K/V isn't one contiguous tensor.
Caches now hand back a per-layer KVHistory holding post-update K, V,
and a MaskApplier that merges the cache's storage restrictions into
the model's logical mask. Models describe their mask in logical
terms; SDPA composes model, padding, and applier contributions and
dispatches to the kernel's causal or no-mask fast path when it can.
KVHistory still exposes K, V, and the composed mask for manual
attention paths (e.g. CUDA prefill at head_dim > 128).
Performance for single-sequence inference is unchanged.
After the rotating buffer has wrapped (c.offset > c.maxSize) a subsequent
L>1 Update() went through a slice-to-[0, c.idx) path that discarded all
slots in [c.idx, Dim), losing the older-but-still-in-window tokens the
first Q of the new batch needs for its sliding-window attention.
Linearize the circular buffer to logical order in that wrapped case so
the existing trim + concat preserves the last (maxSize - 1) old tokens.
When the buffer has not yet wrapped (c.offset <= c.maxSize), slots
[c.idx, Dim) are grow padding or stale post-rewind data, so keep
dropping them.
mlx.Copy shares the backing buffer with its source (via
copy_shared_buffer) rather than allocating independent storage.
When used to snapshot a slice of the KV cache, the snapshot array
holds the entire original cache buffer alive through the shared
data pointer — even after eval detaches the computation graph.
Replace Copy with Contiguous in Snapshot and Split. Contiguous
allocates a compact buffer when the source buffer is significantly
larger than the logical slice (Contiguous::eval checks
buffer_size > nbytes + 16384), which is always the case for KV
cache slices.
Previously, a partial match within a node's edge would truncate the path
to the parent snapshot - effectively making all cache types behave as
recurrent caches. Caches with only transformer layers can rewind to
arbitrary boundary so this restores this capability to improve cache
hits
Enable multiple conversations to reuse cached computations when they
share token prefixes (e.g. the same system prompt). A prefix trie
tracks shared regions so switching between conversations only
recomputes tokens that diverge. Inactive conversation state is paged
from active GPU memory to other memory and restored on demand, with LRU
eviction to keep memory usage bounded.
* prefer rocm v6 on windows
Avoid building with v7 - more changes are needed
* MLX: add header vendoring and remove go build tag
This switches to using a vendoring approach for the mlx-c headers so that Go
can build without requiring a cmake first. This enables building the new MLX
based code by default. Every time cmake runs, the headers are refreshed, so we
can easily keep them in sync when we bump mlx versions. Basic Windows
and Linux support are verified.
* ci: harden for flaky choco repo servers
CI sometimes fails due to choco not actually installing cache. Since it just speeds up the build, we can proceed without.
* review comments
This change adds support for qwen3.5-next-moe models (qwen3-next/qwen3.5-next/qwen3-coder) to the MLX runner. It also:
* introduces recurrent cache support and related MLX ops
* updates pipeline/runner integration and adds tests
* properly quantizes stacked expert tensors
* a Gated Delta Metal kernel for fast SSM inference
* adds new MLX calls for Conv1d, DepthwideConv1d, Contiguous, Exp, Log, SoftmaxAxis
Pass subprocess stdout/stderr through to the parent's stderr directly
instead of re-wrapping each line with slog. The subprocess already
writes structured slog output, so the re-wrapping produced nested
timestamps, levels, and message fields that were hard to read.
Also downgrade verbose KV cache debug logs to trace level.
The KV cache previously used a tree structure which could
store multiple divergent sequences, which is good for cache
reuse. However, this is typically used in conjunction with
paged attention so each node in the tree can store just a
chunk of the KV cache and they can be stitched together later.
We don't currently do this, so the cache was storing copies of
the full cache for each past sequence.
This redundancy plus the lack of resource limits, caused significant
memory use as a conversation grew. Instead, this changes to store
a single entry for the cache, which can be prefix matched. Although
it is less ideal for multiple users, it largely matches Ollama's
current behavior. It can be improved as additional pieces are fleshed
out.
The previous approach tracked array lifecycles through reference
counting, where each array recorded its inputs and a reference count
that was decremented as dependents were freed. This is not really
necessary as MLX tracks references internally. It is also error
prone as it is easy to create new arrays and forget to free them
when the Go variable goes out of scope.
Instead, we can pin just the arrays we want (typically outputs and
specific intermediates, like the cache). All other arrays are freed
by default when we run sweep. This avoids most causes of memory leaks
while still giving the freedom to save what we want.
This change adds a new MLX based runner which includes:
* Method-based MLX bindings
* Subprocess-based MLX runner (x/mlxrunner)
* KV cache with tree management
* A basic sampler
The GLM4-MoE-Lite model has been ported to use the new bindings.
---------
Co-authored-by: Michael Yang <git@mxy.ng>
