Under LLAMA_SLEEP_EVICT_KV a cold model still held the scheduler's worst-case
compute buffer (hundreds of MiB, e.g. ~700 MiB for gemma-26B) plus the resident
experts. release_device(evict_kv) now also frees the sched (sched.reset() +
sched_need_reserve), and restore_device() rebuilds it via sched_reserve(), so a
fully-evicted model holds essentially no VRAM (gemma cold: 7147 -> 51 MiB).
Trades a heavier re-warm (weights+KV H2D + sched reserve) for the freed VRAM;
weights-only mode is unchanged (fast switch, keeps KV+compute).
Assisted-by: Claude
Extend on-demand device residency to the KV cache so that when a model's KV
plus another model would not fit in VRAM, the KV can also be evicted to a host
shadow (D2H on release, H2D on restore) instead of only the weights.
- llama_memory_i: add release_device_buffers()/restore_device_buffers()
(default no-op). Implemented in llama_kv_cache (D2H shadow of the live
ctxs_bufs, freed and reallocated like the weights); llama_memory_hybrid and
llama_kv_cache_iswa delegate to their child caches.
- llama_context::release_device(evict_kv): also evict the memory's device
buffers when requested; restore_device() rebuilds them. Public API
llama_context_release_device gains an evict_kv flag.
- server: LLAMA_SLEEP_EVICT_KV=1 enables it. Off by default (weights-only),
since the KV shadow adds a D2H/H2D copy of the live cache each cycle.
Validated on RX 580 (Vulkan), 4B @ 32k ctx: weights-only cold VRAM 1750 MB
(KV stays); weights+KV cold VRAM 726 MB (KV freed, ~1 GB reclaimed). KV
survives the round-trip: prompt cache reused after the cycle (prompt_n 4 vs
42), correct output.
Assisted-by: Claude
Add release/restore of a model's GPU weight buffers (keeping a host shadow
and the KV cache) so several always-loaded llama-server processes can
time-share a single GPU without reloading or losing the prompt cache.
- llama-model: release_device_weights()/restore_device_weights() capture a
compact host shadow (stable iteration order, view-skipping) and free then
realloc the device weight buffers; weights_resident() query.
- llama-context: release_device()/restore_device() wrappers; decode() auto-
restores; public C API llama_context_release_device/restore_device.
- server: LLAMA_SLEEP_VRAM_ONLY makes idle-sleep release only the VRAM weights
(not a full unload/reload). A cross-process flock token in LLAMA_VRAM_ARENA
enforces "resident iff holds token"; an inotify doorbell forces the holder
to release on contention. The warden thread only touches the task queue, so
releases run on the loop thread and never race a decode.
Validated on RX 580 (Vulkan): two models share 8GB, never both resident,
correct output under contention, KV cache preserved (no re-prefill).
Assisted-by: Claude
* convert: add dsv4 conversion
* add basic setup
* add llm_graph_input_dsv4
* add save-load state
* add sinkhorn eps - correction by @fairydreaming
* add rope fix
* cleanup dead code
* fix bugs
* support pro model: added by @fairydreaming
* remove redundant V cache
* Chat template
* remove debugging leftovers
* Add mechanism for inlining templates based on architecture
* s/deepseek-v4-flash/deepseek4/g
* s/deepseek-v4-flash/deepseek4/g continued
* enable graph reuse
* enable FA
* fix test llama archs
* rename
* compatibility with antirez ds4 GGUFs
* simplified set_gguf_parameters() by calling super class method, replaced moe.score_func with expert_gating_func.
* reserve worst-case kv-cache
* revert max split inputs
* address review comments
* add padding to enable FA
* pad only the final value of plan.n_kv to 256
* remove built-in cpp chat template
* cont: remove cpp built-in template
* rm outdated test
* replace ggml_view_3d() with ggml_reshape_3d()
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* only support n_seq=1 for now
* remove unused var
* cont: remove unused var
* use scale bias
* use correct ptr for can_reuse
* remove gen-chat-inline-templates.py
* simplify graph reuse
* cont: cleanup
* remove unused inputs
* enable partial checkpointing
* add correct shape for kq_mask + set llama_model_n_swa to 0 for dsv4
* precompute source_idx + add comment about dummy write
* support multi-seq
* remove restored_trim_pos
* use split_equal when possible
* fix indent
* address review comments
* use LLM_KV
* fix ci
---------
Co-authored-by: Piotr Wilkin <piotr.wilkin@syndatis.com>
Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
Co-authored-by: fairydreaming <166155368+fairydreaming@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* speculative : add common_speculative_n_max helper function
Extract the speculative max-draft-size logic from server_n_outputs_max
into a reusable common_speculative_n_max() function in common/speculative.
Assisted-by: llama.cpp:local pi
* cont : draft context always has n_parallel outputs
* llama : log n_outputs_max
* speculative : remove draft-simple auto-enable
* ci : enable server tests on PRs
* llama: save more VRAM by reserving n_outputs == n_seqs when possible
* add n_outputs_per_seq
* move n_outputs_max to server-context
* change ubatch to batch everywhere
* Move to backend sampling for MTP draft path
Run top_k(10) on the draft backend. D2H transfers happen only for the top 10 logits
Make backend sampling more robust and fallback to CPU on failure cases, such as with "-sm tensor" or when a backend doesn't support TOP_K.
* Allow sampler chains to be partially offloaded to backend
* Add --spec-draft-backend-sampling argument. Enabled by default.
* spec: support MTP
* fix batch size
* rename files
* cont : simplify (#7)
* MTP: clean-up (#9)
* MTP: clean-up
* review: use llama_context_type instead of llama_graph_type
* review: remove llama_model_has_mtp
* review: fix convert issues
* convert: fix pycheck
* review: formatting
* use `mtp-` for identifying mtp models
* convert: fix mtp conversion
* mtp -> draft-mtp
* remove unused llama_arch
* add need_embd in speculative
* llama: allow partial seq_rm for GDN models for speculative decoding
Currently speculative checkpoint needs to restart from a checkpoint
after some draft tokens are not accepted, this leads to some wastage in
running the target again. This PR adds the ability to rollback upto
`draft_max` by storing the GDN intermediates.
* fix pending state
* vulkan: add GDN partial rollback
* meta: extend check to axis 1
* metal: add GDN partial rollback
Extend the gated delta net kernel to store intermediate states for
partial rollback support on the Metal backend.
- Add K (snapshot slot count) as a function constant
- Read input state from slot 0 of the 3D state tensor
- Write intermediate states to different slots during token loop
- For K=1, maintain backward-compatible single-slot behavior
Ref: https://github.com/ggml-org/llama.cpp/commit/8c05923630110223669f069af2000e9cf10c02bc
Assisted-by: llama.cpp:local pi
* delta_net_base: use ggml_pad instead of new_tensor
* review: add need_rs_seq
* review: rename part_bounded to n_rs
* review: deslop comments
* review: rename, add asserts
* server : adjust checkpoint logic (#11)
* server : adjust checkpoint logic
* cont : rm asserts
* server-context: fix early exit
* spec : fix compatibility with n-gram and add TODOs (#13)
* metal : cleanup
* llama : fix faulty bitwise check in recurrent memory
* server : disable RS-based MTP in combination with other spec types
* spec : add TODOs
* cont : fix comment
* cont : update comment
* common : fix logic for ngram + mtp compat
* llama-memory: enable checkpointing with partial rollback
* cont: add test-case for loading into a dirty ctx
* llama-memory-recurrent: clear rs_idx in clear
* download: fix mtp path
* llama-arch: fix enorm op
* docs: update docs
* conversion: fix type annotations
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* spec : refactor
* spec : drop support for incompatible vocabs
* spec : update common_speculative_init()
* cont : pass seq_id
* cont : dedup ctx_seq_rm_type
* server : sketch the ctx_dft decode loop
* server : draft prompt cache and checkpoints
* server : improve ctx names
* server, spec : transition to unified spec context
* cont : sync main and drft contexts
* cont : async drft eval when possible
* cont : handle non-ckpt models
* cont : pass correct n_past for drafting
* cont : process images throught the draft context
* spec : handle draft running out of context
* server : fix mtmd draft processing
* server : fix URL for draft model
* server : add comment
* server : clean-up + dry
* speculative-simple : update
* spec : fix n_past type
* server : fix slot ctx_drft ptr
* tools : update readme
* naming : improve consistency
* spec : refactor for multi-sequence speculative context
* cont : prepare params
* cont : prepare params
* spec : support parallel drafts
* server : support parallel drafting
* llama : reuse device buffers when possible
* server, spec : clean-up
* cont : clean-up
* cont : minor
* spec : reset `drafting` flag at the end
* spec : introduce `common_speculative_process()`
* spec : allow for multiple spec types (chain of speculators)
* replace old type field of type common_speculative_type in the
common_params_speculative struct with a vector to allow multiple
types to be specified
* introduce common_get_enabled_speculative_impls(const std::vector<enum common_speculative_type>)
to figure out which implementations the user has enabled
* introduce common_speculative_type_from_names(const std::vector<std::string> & names)
to parse the already user provided spec types
* all speculators run sequentially, best one wins (we verify its drafted tokens)
* maximize expected accepted tokens for current round by calculating the
product between the probability of accepting current token (n_acc_tokens / n_gen_drafts)
and the draft's length
---------
Co-authored-by: Petros Sideris <petros.sideris@nokia.com>
* ggml: backend-agnostic tensor parallelism
* support for GPT-OSS, Qwen 3 MoE
* partial Vulkan fix
* add support for 4/8 GPUs
* unconditional peer access
* re-use buffers + ggml contexts
* fix output pattern
* NCCL support
* GGML: HIP: add RCCL support
* Remove shfl and AllReduce from backend interface
* move allocation workaround out of ggml-alloc.c
* 2d tensor set/get support
* Fix the seg fault without NCCL
* Apply suggestion from JohannesGaessler
* support for tensor dims % n_devs != 0
* fix view_offs scaling
* arbitrary num. of GPUs/tensor split
* fix compilation
* better granularity estimate
* Support device-specific host buffer types if all underlying backends expose the same type. This allows using pinned memory instead of pageable memory for CUDA.
Fix compilation errors.
* partial Qwen 3 Next support
* Fix qwen3 30b (#8)
* Fix crash with Qwen-30B-A3B Q4_0
Qwen-30B-A3B Q4_0 has an intermediate dimension of 768. Using a granularity of 256 forces an uneven split between GPUs, which is not supported by the current implementation.
* Decide block size based on tensor quantization type
* Fix crashes due to KV cache serialization (#9)
KV cache serialization requires non-zero offsets on the tensor. Add support in the meta backend to set/get a tensor with a non-zero offset.
* metal : fix build (#7)
* static memory allocations, fix usage count
* fix tensor granularity
* more even memory distribution
* use BF16 for allreduce
* rebase fixup
* better error message for unsupported architectures
* Fix device mismatch during scatter of allReduce. (#11)
There is a mismatch between the dst buffer device and the backend device, causing the use of sync copies
* Enable the previous allreduce implementation. It is better in both perf and stability (#12)
* delay AllReduce for Moe for less I/O
* build : clean-up compile warnings
* backend : move most of the meta backend API to ggml-backend-impl.h
* cont : hide unused public API in the implementation
* llama : use llama_device + remove ggml_backend_dev_is_meta()
* ggml-backend : remove unused alloc include
* minor : remove regex include
* ggml : introduce ggml-ext.h for staging new APIs
* rebase fixup
* fix tests
* llama : more robust logic for determining Meta devices (#16)
* llama : more robust logic for determining Meta devices
* cont : fix devs size check
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
* cont : fix log type
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
---------
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
* disable roundtrip for meta backend
* fix arch selection
* Qwen 3.5 support
* fix Gemma 4 MoE
* fix OpenVino, SYCL
* fix test-llama-archs for CPU-only builds
* Fix Qwen 3.5 MoE
* disable meta backend tests for WebGPU
* tests : filter CPU-based devices from the Meta backend tests (#17)
* meta : formatting, naming, indentation (#18)
* formatting : llama-model.cpp
* formatting : ggml-ext.h
* formatting : ggml-backend-meta.cpp
* meta : add TODO
* add documentation
* better error messages
* fix GPT-OSS
---------
Co-authored-by: Carl Philipp Klemm <carl@uvos.xyz>
Co-authored-by: Gaurav Garg <gaugarg@nvidia.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
The MEAN/CLS/LAST pooling paths in encode() and decode() used
n_embd_inp() (16384 for qwen3vl with deepstack) to read from the
pooled embedding tensor, which only has n_embd_out() (4096) floats
per sequence. This caused a tensor read out of bounds assertion.
Fixes embedding mode for Qwen3-VL-Embedding models.
* context: zero output buffer on allocation
Address GHSA-wqq9-25mr-rw76.
The logits output buffer allocated in output_reserve() uses
posix_memalign(), which does not zero memory. The buffer is only
written during decode when needs_raw_logits() returns true. When
backend samplers cover all output sequences, needs_raw_logits()
returns false and the buffer is never written, but
llama_get_logits() still returns a pointer to it, exposing stale
heap content.
Zero the buffer after allocation to prevent information disclosure
through the public logits API.
Found-by: Pwno
* Update src/llama-context.cpp
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* llama : fix pooling assertion crash in chunked GDN detection path
The chunked fused Gated Delta Net detection in sched_reserve() calls
graph_reserve(16*n_seqs, n_seqs, n_outputs, ...) where n_outputs = n_seqs.
This creates a dimension mismatch in build_pooling() for embedding models
with mean/rank pooling: build_inp_mean() creates a tensor with shape
[n_tokens=16*n_seqs, ...] while t_embd is reduced to [n_outputs=n_seqs, ...]
via out_ids, causing ggml_mul_mat to assert on ggml_can_mul_mat(a, b).
Fix: pass n_tokens as n_outputs in the chunked GDN graph reservation,
matching the pattern used by the pp/tg worst-case reservations.
Regression introduced by #20340 (d28961d).
Same class of bug as #12517, fixed by #12545.
* server : add mean pooling tests to embedding test suite
Add test_embedding_pooling_mean and test_embedding_pooling_mean_multiple
to cover the --pooling mean codepath, which was previously untested.
These tests would have caught the regression introduced by #20340 where
build_pooling() crashes with a ggml_mul_mat assertion due to mismatched
dimensions in the chunked GDN detection path.
---------
Co-authored-by: Domenico Crupi <domenico@zerovolt.it>
* tests: allow loading test-backend-ops tests from json
* add error threshold based on op
* add error when file cannot be read
* add graph operator json extraction tool
* add nb parameter for non-contiguous input tensors
* fix view check
* only use view if non-contiguous/permuted, use C++ random instead of rand()
* replace internal API calls with public llama_graph_reserve call
* reduce test description length
* fix nb[0] not getting set for view
* add name to tests
* fix inplace error
* use text file instead of json
* move llama_graph_reserve function to new llama-ext header, move export-graph-ops to tests/
* fix missing declaration
* use pragma once
* fix indent
* fix Windows build
* llama : enable chunked fused GDN path
* models : avoid Q and K repeats when using fused GDA
* cont : fix comment
Co-authored-by: Aman Gupta <amangupta052@gmail.com>
* cont : fix the fix
Co-authored-by: Aman Gupta <amangupta052@gmail.com>
* cont : fix
* metal : add GDN kernel (#20361)
* metal : add Metal backend for GGML_OP_GATED_DELTA_NET
Add a fused Metal kernel for the gated delta net recurrence op
(#19504), enabling GPU-accelerated inference for DeltaNet-based
models (Qwen3.5, etc.) on Apple Silicon.
Supports both GDA (scalar gate) and KDA (per-row gate) modes
with head_size 64 and 128. Unsupported configurations (head_size
32, non-contiguous tensors) gracefully fall back to CPU.
Performance: Qwen3.5-0.8B Q4_K_M on M4 Max
tg128: 170 -> 213 t/s (+25%)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* metal : validate contiguity of all input tensors in supports_op
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* metal : add algorithm equivalence comment for GDA decay path
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* cont : unslop + optimize
* cont : clean-up
---------
Co-authored-by: Paul Flynn <paul@arkavo.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* CUDA: AR gated delta net improvements (#20391)
* Add FastDiv to gated_delta_net_cuda
* Shard columns across warps
This reduces register pressure (avoids spill for S_v = 128) and gives
the warp-scheduler more CTAs to schedule (thus hiding data-access
latencies).
* Remove unneded include in gated_delta_net.cu
* Improve comments
* Apply code-formating
* Make sharding HIP-compatible
1. Use ggml_cuda_get_physical_warp_size() to determine warp size flexibly
2. Add test with partial warp to test sum reduction on CUDA
* Remove fastdiv_s64, as we can treat neqk1 and rq3 as uint32_t
* Rename variables
* Enable GDN also for prefill, move TODO for chunked_GDN
* Actually remove the TODO from 206890897546bd16602c3b79394fd5ea09ef199f
* Get warp size at runtime
warp_size is not known at compile time in hip host code.
* Don't expose ggml_cuda_get_physical_warp_size on host
---------
Co-authored-by: uvos <devnull@uvos.xyz>
* llama : refactor llm_build_delta_net_base API
---------
Co-authored-by: Aman Gupta <amangupta052@gmail.com>
Co-authored-by: Paul Flynn <paul@arkavo.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Oliver Simons <osimons@nvidia.com>
Co-authored-by: uvos <devnull@uvos.xyz>
* tests: add end-to-end tests per model architecture
* fixup for rebase
* fix use-after-free in llama-model-loader.cpp
* fix CI
* fix WebGPU
* fix CI
* disable CI for macOS-latest-cmake-arm64
* use expert_weights_scale only if != 0.0f
* comments
* llama : remove write/read of output ids/logits/embeddings
This commit removes the write/read of output ids, logits and
embeddings from the llama context state.
Refs: https://github.com/ggml-org/llama.cpp/pull/18862#issuecomment-3756330941
* completion : add replying of session state
This commit updates the session handing in the completion tool to handle
the that logits are no longer stored in the session file. Instead, we
need to replay the last token to get the logits for sampling.
* common : add common_prompt_batch_decode function
This commit adds a new function which is responsible for decoding prompt
and optionally handle the saving for session data.
* update save-state.cpp to use llama_state_load_file
This commit updates the save-load-state example to utilize the new
llama_state_load_file function for loading the model state from a file.
And it also replays the last token after loading since this state is now
stored before the last token is processed.
* examples : set n_seq_max = 2 for ctx3
This commit updates the save-load-state example to set the n_seq_max
parameter to 2 when initializing the ctx3 context.
The motivation for this change is that using 1 as n_parallel/n_seq_max
the context only supports one sequence, but the test laster tries to
use a second sequence which results in the following error:
```console
main : loaded state with 4 tokens
main : seq 0 copied, 225760 bytes
main : kv cache cleared
find_slot: seq_id=1 >= n_seq_max=1 Try using a bigger --parallel value
state_read_meta: failed to find available cells in kv cache
```
This seems to only happen for recurrent/hybrid models.
This commit updates get_logits_ith(), and get_embeddings_ith() to use
output_resolve_row() to resolve the batch index to output row index.
The motivation for this is to remove some code duplication between these
functions.
* full modern bert support
* added gelu op in rank pooling for modern bert
* still working on stuff, added mean calculation before classifier head
* Update convert_hf_to_gguf.py
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* first layer is dense, as per modern bert research paper
* Update src/llama-graph.cpp
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* fixed set input for mean pooling to check if pooling type is ranking since modern bert does mean & rank
* Update src/llama-graph.cpp
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* Update convert_hf_to_gguf.py
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
---------
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
Lumpiasty
