* ci : add older, min and dry-run options to ccache-clear
Assisted-by: pi:llama.cpp/Qwen3.8-27B
* pi : add note about not wrapping lines in PR descriptions
[no ci]
Assisted-by: pi:llama.cpp/Qwen3.8-27B
* metal: dequantize q8_0 KV to f16 before flash attention
Add a preprocessing pass for GGML_OP_FLASH_ATTN_EXT on the Metal backend:
when the KV cache is quantized (Q8_0 for now), dequantize K and V into a
contiguous F16 scratch buffer and run the existing F16 flash attention
kernels on it, instead of the in-kernel dequantization path.
- new kernel kernel_flash_attn_ext_dequant_to_f16<block_t, QK, deq_t4x4>:
one thread per quant block (K then V), stride-aware so permuted KV is
supported; instantiated for Q8_0 (extending to Q4_0/Q4_1/Q5_0/Q5_1 is
one instantiation + one gate case)
- the gate is type-only: dequantize whenever the KV is quantized,
regardless of head sizes, GQA ratio or n_kv; the attention kernels
themselves are untouched
- the F16 copies live in the op's own scratch allocation
(ggml_metal_op_flash_attn_ext_extra_dequant_f16); the KV pad kernel
reads the dequantized buffers when the path is active
- the FA pipeline getters gain a use_f16_kv flag selecting the existing
f16 kernels and contiguous strides
- ref: https://github.com/ggml-org/llama.cpp/pull/25556
Verification (M2 Ultra):
- test-backend-ops test -o FLASH_ATTN_EXT: 4798/4798 pass, including the
new q8_0 eval cases (decode/prompt, permuted, sinks+ALiBi+softcap,
kv=113 pad path, kv=16384)
- llama-perplexity on Qwen2.5-0.5B with -ctk q8_0 -ctv q8_0 matches the
f16 KV reference (PPL 1.0008 vs 1.0008)
Assisted-by: pi:llama.cpp/Qwen3.8-27B
* metal : launch the FA KV dequant kernel separately for K and V
Simplify kernel_flash_attn_ext_dequant_to_f16: it now dequantizes a single
tensor (its own ne/nb and dst) with no is_v branching, and the op dispatches
it twice with the same pipeline - once for K and once for V. The kargs
struct shrinks to a single ne/nb set plus nblocks.
Assisted-by: pi:llama.cpp/Qwen3.8-27B
* metal : dequantize q4_0, q4_1, q5_0 and q5_1 KV to f16 before flash attention
The dequant pass now covers all quantized KV types supported by the Metal
flash attention kernels. The dequant kernel, kargs, scratch allocation and
dispatch are type-generic, so each type is one kernel instantiation plus one
gate case.
Assisted-by: pi:llama.cpp/Qwen3.8-27B
* metal : skip the redundant V dequant when V is a view of K
In MLA-based models, the V of the FA op is a view of K (the first ne20
elements of each K row); the dequantized V is then a view of the dequantized
K, so skip the second dequant dispatch, do not reserve the V scratch region,
and let the pad and attention kernels read V from the K F16 buffer with K's
strides. The detection follows the CUDA backend:
V->view_src && (V->view_src == K || (V->view_src == K->view_src && V->view_offs == K->view_offs))
Also fix the FA pipeline getters: ns10/ns20 are function constants baked into
the kernels and must be the actual K/V row widths as seen by the kernel. The
dispatch now passes them explicitly (nb11_attn/nb10_attn, nb21_attn/nb20_attn)
instead of the getters assuming contiguous F16 KV (ns20 = dv), which was wrong
when V is read from K with K's row pitch (e.g. 576 vs 512).
New test cases: 576/512 q8_0 (MLA shape, V is a view of K) at kv=113 (KV pad),
nb=1 (vec) and nb=64 (non-vec).
Assisted-by: pi:llama.cpp/Qwen3.8-27B
* test : remove backend-specific wording from test-backend-ops comments
Assisted-by: pi:llama.cpp/Qwen3.8-27B
* pi : avoid backend mentions in test-backend-ops comments
Assisted-by: pi:llama.cpp/Qwen3.8-27B
* metal : rename the FA dequant_f16 identifiers to kv_f16
Assisted-by: pi:llama.cpp/Qwen3.8-27B
* cont : clean-up
* cont : remove TODO
* ci : parallelize platform builds in build-xcframework.sh
The ios-xcode release job builds 7 platform/simulator configurations
sequentially, each with -j $(nproc). Run them with at most 3 concurrent
builds (the release runner has 3 cores), splitting the cores between the
builds (-j 1 each on the runner), so total CPU pressure is unchanged while
the build phase runs about 2.3x faster.
- convert the 7 build blocks into functions (flags unchanged)
- add a run_builds_parallel pool: 3-slot sliding window, per-build logs,
dumps the failing log and aborts on error (background job failures do
not trigger set -e)
- queue the 2-arch builds first so the slower builds occupy the slots early
Assisted-by: pi:llama.cpp/Qwen3.8-27B
* pi : add guideline for comments
* cont : disable 5/7 builds
* ci : make build-xcframework.sh builds configurable via CLI args
The script now takes an optional list of builds to run
(ios-sim ios-device macos visionos visionos-sim tvos-sim tvos-device);
with no arguments it builds all of them, as before. The per-build
lists for the build pool, framework setup, static library combining
and xcframework creation are now driven by a single build_spec
lookup instead of four hardcoded (partially commented-out) lists.
release.yml builds only macos and ios-device to cut the build time.
Assisted-by: pi:llama.cpp/Qwen3.8-27B
* pi : update
* ci : fix ios build
* ci : fix andoroid
* ci : fix apple builds
* cmake : add install() for impl libraries
Add install(TARGETS <target> LIBRARY) for all -impl libraries that were
changed from STATIC to shared (controlled by BUILD_SHARED_LIBS) in
commit bb28c1fe2. Without this, cmake --install fails to copy the shared
libraries, causing runtime errors like:
llama-server: error while loading shared libraries: libllama-server-impl.so
Ref: https://github.com/ggml-org/llama.cpp/issues/23494#issuecomment-4512912515
Assisted-by: llama.cpp:local pi
* ci : fix xcframework build
* save-load-state : refactor into separate phase functions
- Split monolithic main() into 4 self-contained phase functions, each
managing its own context/sampler/batch lifecycle
- Each function tokenizes internally using its local ctx instance
- main() is now a clean orchestrator: init -> run phases -> assert results
- Proper resource cleanup on every exit path (return {} on error)
Assisted-by: llama.cpp:local pi
* save-load-state : use params.out_file instead of separate state_file
- Remove state_file parameter from all phase functions
- Each function accesses params.out_file directly
- Initialize params.out_file in main alongside params.prompt
Assisted-by: llama.cpp:local pi
* save-load-state : use smart pointers for ctx and smpl
- Replace raw llama_context* with llama_context_ptr
- Replace raw llama_sampler* with llama_sampler_ptr
- Remove all manual llama_free() and llama_sampler_free() calls
- Keep llama_batch as raw (managed manually with llama_batch_free)
Assisted-by: llama.cpp:local pi
* save-load-state : add local llama_batch_ptr RAII wrapper
- Add llama_batch_ptr struct holding llama_batch by value
- Calls llama_batch_free() in destructor
- Eliminates all manual llama_batch_free() calls
Assisted-by: llama.cpp:local pi
* save-load-state : replace printf/fprintf with logging macros
- Add log.h include
- Replace fprintf(stderr, ...) errors with LOG_ERR
- Replace fprintf(stderr, ...) info with LOG_TRC
- Replace printf output with LOG
Assisted-by: llama.cpp:local pi
* save-load-state : refactor tests to check results inline
Each follow-up phase now accepts an expected result and performs
the comparison internally instead of collecting results in main().
Assisted-by: llama.cpp:local pi
* save-load-state : improve test output readability
Add phase labels, remove redundant run prefixes, and show
PASS after each test.
Assisted-by: llama.cpp:local pi
* pi : add rule about git signing
* save-load-state : simplify llama_batch_ptr
Change get() to return a reference and remove operator*().
Use batch.get() throughout for consistency.
Assisted-by: llama.cpp:local pi
* save-load-state : extract generate_tokens helper
Factor out the repeated token generation loop into a shared
helper function used by all phases.
Assisted-by: llama.cpp:local pi
* save-load-state : update comments to use test terminology
Replace "Phase" with "Test" and list each test's steps
as bullet points.
Assisted-by: llama.cpp:local pi
* save-load-state : rename test functions
Rename to test_baseline, test_state_load, test_seq_cp_host,
test_seq_cp_device. Update comments and logs accordingly.
Assisted-by: llama.cpp:local pi
* pi : add rule to never git push without confirmation
Assisted-by: llama.cpp:local pi
* common : add model_only option to common_init_from_params
Add bool model_only parameter to skip context creation,
sampler init, and context-dependent setup.
Use in save-load-state to initialize only the model,
with each test creating its own context.
Assisted-by: llama.cpp:local pi
---------
Co-authored-by: ggerganov <[email protected]>
* docs : update speculative decoding parameters after refactor (#22397)
Update docs/speculative.md to reflect the new parameter naming scheme
introduced in PR #22397:
- Replace --draft-max/--draft-min with --spec-draft-n-max/--spec-draft-n-min
- Replace --spec-ngram-size-n/m with per-implementation variants
- Add documentation for all new --spec-ngram-*- parameters
- Update all example commands
Assisted-by: llama.cpp:local pi
* pi : add rule to use gh CLI for GitHub resources
Assisted-by: llama.cpp:local pi
* docs : run llama-gen-docs
* arg : fix typo
Georgi Gerganov
