* common: auto-download dflash- and eagle3- HF sidecars
Mirror the existing mtp- sidecar logic to support auto-discovery and
download of DFlash (dflash-) and Eagle3 (eagle3-) speculative decoding
sidecars from Hugging Face repos.
Changes:
- Add --dflash and --eagle3 CLI flags to trigger sidecar download
- Add find_best_dflash() and find_best_eagle3() using find_best_sibling
- Exclude dflash- and eagle3- filenames from primary model selection
- Filter dflash- and eagle3- from cached model listings
- Wire download tasks that set speculative.draft.mparams as fallback
Assisted-by: pi:llama.cpp/Qwen3.6-27B
* docs : regen
* ci : add HF_TOKEN to self-hosted workflows
Pass the HF_TOKEN_CI repo secret as HF_TOKEN env var in the self-hosted
build and server workflows.
Fix the stale build.yml path reference.
Assisted-by: pi:llama.cpp/Qwen3.6-27B
* cont : add comment
---------
Co-authored-by: ggerganov <ggerganov@users.noreply.github.com>
* server : clear checkpoints upon prompt clear
* server : move the prompt state data to the server_prompt_cache
Assisted-by: pi:llama.cpp/Qwen3.6-27B
* server : handle batched slot being cleared
dict.get("key", default) returns None (not default) when the key
exists but its value is explicitly None. This caused an AttributeError
in _escape_html() when a task errored before grading and answer was
set to None.
Assisted-by: pi:llama.cpp/Qwen3.6-27B
Absorb get_slot_by_id logic into get_available_slot so slot selection
is handled by a single function call. When a specific slot id is
requested, the LCP similarity check still runs to enable proper
prompt cache updates.
Assisted-by: pi:llama.cpp/Qwen3.6-27B
Reuse existing rope kernels with a function constant to toggle forward/backward
rotation, avoiding duplicate kernel code.
Assisted-by: pi:llama.cpp/Qwen3.6-27B
* metal : add f16 and bf16 support for concat operator
Extend the Metal backend concat operator to support f16 and bf16 tensor
types in addition to the existing f32 and i32 support.
- Template kernel_concat on type T with specializations for float, half,
bfloat, and int
- Add type-specific pipeline getter ggml_metal_library_get_pipeline_concat()
- Update device support check to allow f16 unconditionally and bf16 when
device supports bfloat16
- Update dispatch to select the correct kernel specialization by type
Assisted-by: pi:llama.cpp/Qwen3.6-27B
* metal : extend concat operator to support f16, bf16, i8, i16 and i64
Assisted-by: pi:llama.cpp/Qwen3.6-27B
When reasoning-budget is set in model.ini, the per-request
thinking_budget_tokens from the WebUI was ignored because the
model.ini value took unconditional precedence.
Swap the precedence so the WebUI per-request value is checked
first, with the model.ini value serving as a fallback default.
Assisted-by: pi:llama.cpp/Qwen3.6-27B
* tests : refactor test-save-load-state to accept token input
- Default prompt is now empty; when not provided, generate n_batch
random tokens (useful for models without a tokenizer)
- Tokenization happens once upfront; pass token vector to test functions
- generate_tokens prints token IDs instead of decoded pieces
- Use llama_model_get_vocab / llama_vocab_n_tokens API
- Upgrade log level from LOG_TRC to LOG_INF for visibility
Assisted-by: llama.cpp:local pi
* cont : use llama_tokens alias
Reduce the number of parallel jobs in server-self-hosted.yml by stacking
test configurations as sequential steps within a single job, following the
pattern from #23927.
- server-metal: 4 matrix jobs -> 1 job with 4 sequential test steps
- server-cuda: 2 matrix jobs -> 1 job with 2 sequential test steps
- server-kleidiai: removed unnecessary single-entry matrix
- removed unused Setup Node.js step from server-metal
Total: 7 parallel jobs -> 3 parallel jobs
Assisted-by: llama.cpp:local pi
* 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
Fixes: https://github.com/ggml-org/llama.cpp/pull/23927#discussion_r3332213086
The cpu-x64-high-perf job was missing the Linux label in its runs-on
specification, causing the runner to not be discovered. All other
self-hosted Linux jobs include this label.
Assisted-by: llama.cpp:local pi
* ci : disable libcommon build from xcframework
* ocd : fix name
* ci : ios-xcode change to macos-26
* cont : pin xcode
* cont : pin xcode to minor version
* ci : ios use macos-15 again
* ci : add and test ccache-clear
* cont : fix
* cont : set permission
* cont : another permission
* cont : token
* cont : print key
* cont : bring back perms
* cont : test windows
* cont : add token
* cont : cleanup
* ci : make release jobs clean-up their ccache
* ci : separate CUDA windows workflow + fix names
* ci : rename workflow
* ci : prefix cache names with workflow name
* ci : rename build.yml -> build-cpu.yml
* ci : cache keys
* ci : fix windows cuda/hip concurrency of release workflow
* ci : fix apple cache names
* ci : add TODOs
* cont : keep just the last cache
* ci : update release concurrency to queue
* ci : move the release trigger to ubuntu-slim
* ci : hip add TODO
* cont : improve words
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* ci : server windows set build type explicitly
* cont : try windows-2025
* ci : use llvm
* cont : use ninja
* cont : fix shell
* ci : set number of jobs correctly
* ci : fix windows with vulkan ccache by using llvm
* ci : server ccache only on master
* ocd : fix job names
[no release]
* ci : fix undefined sanitizer build to use Debug build type only
* ci : ccache the server builds
* cont : remove ui dependency + reuse ccache for both ubuntu jobs
* tmp : force ccache save
* Revert "tmp : force ccache save"
This reverts commit a857b03a10.
* cont : no need for node.js
* ci : move [no release] check to dedicated check_release job
Move the workflow-level \`if\` condition that skips builds when the commit
message contains \`[no release]\` into a lightweight \`check_release\` job.
All build jobs now depend on it via \`needs\` and check its output.
This ensures the skip logic is evaluated at the job level rather than at
the workflow level, which is the recommended approach for conditional jobs.
Assisted-by: llama.cpp:local pi
* cont : use `fast` runner
* ci : skip release workflow on master when commit message contains [no release]
Assisted-by: llama.cpp:local pi
* ci : restrict sanitizer builds to x86_64 + fix build type
the spark is apparently too slow for some reason
* tests : fix undefined warning
[no ci]
* ci : disable SYCL f16 builds
* ci : extract android and hip into separate workflows
* ci : move webgpu to separate workflow
* ci : move the rpc to a separate workflow
* ci : extract s309x and ppcl jobs
* ci : extract opencl job into a separate workflow
* ci : remove tag from build-self-hosted.yml
* ci : slim -> self-hosted
* ci : prevent heavy CPU jobs from running on fast runners
* ci : prevent cmake pkg to run on dedicated fast runners
* ci : try to bump 3.11 -> 3.13
* ci : move lint back to 3.11
* ci : back to 3.11
* ci : add comment about UI jobs
* ci : move python requirements check to CPU runners
this job is a bit slow for a dedicated "fast" runner
* ci : add self-hosted ui workflow
* ci : fix UI naming
* tmp to check if arm64 fast is compatible with all jobs
* revert last commit
* 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
* cmake : remove STATIC from impl libraries, allow BUILD_SHARED_LIBS control
Remove explicit STATIC from all -impl libraries (server, cli, completion, bench,
batched-bench, fit-params, quantize, perplexity) so BUILD_SHARED_LIBS controls
shared vs static linkage.
Add WINDOWS_EXPORT_ALL_SYMBOLS ON for proper DLL export on Windows.
Assisted-by: llama.cpp:local pi
* cmake : enable LLAMA_BUILD_APP by default
Assisted-by: llama.cpp:local pi
* ci : disable app in build-cmake-pkg.yml
* tests : move save-load-state from examples to tests
- Move examples/save-load-state/ to tests/test-save-load-state.cpp
- Remove subdirectory reference from examples/CMakeLists.txt
- Add test to tests/CMakeLists.txt as a model test
- Remove CODEOWNERS entry for removed example directory
Assisted-by: llama.cpp:local pi
* cont : update ci
* metal : fix GGML_OP_SET kernel threads
* tests : extend test_cpy to support different src/dst shapes
Extend test_cpy to support different source and destination tensor shapes
for CPY operations (reshaping), where the total number of elements must match.
- Renamed ne -> ne_src, added ne_dst parameter (default: use src shape)
- Added 50 new reshaping test cases covering 1D<->2D<->3D<->4D conversions
- Tests exercise 1024 boundary, small shapes, and large dimensionality changes
- Fixed dangling reference bug (storing & to temporary std::array)
- Updated all existing test calls with permute/transpose args for compatibility
Assisted-by: llama.cpp:local pi
* metal : optimize concat kernel with row batching for small widths
When ne0 < 256, batch multiple rows into a single threadgroup to improve
occupancy. This avoids underutilizing the GPU when processing narrow tensors.
- Dispatch nth = min(256, ne0) threads per group
- Calculate nrptg (rows per threadgroup) to fill up to 256 threads
- Update kernel index calculation to handle the row batching
- Add boundary check for i1 >= ne1
Assisted-by: llama.cpp:local pi
* tests : clean-up
* tests : refactor CPY shape tests to use dimension permutations
Replace 75 hardcoded test cases with a loop over permutations of
{3, 5, 7, 32} (total elements: 3360). Each src permutation is tested
against canonical sorted and reverse dst, skipping identical shapes.
Covers F32, F16, and Q4_0 (when both src and dst ne0 == 32).
Assisted-by: llama.cpp:local pi
ggml_backend_dev_by_name always appends a nullptr sentinel to the devices
vector. Skipping nullptr entries prevents assertion failure in
ggml_backend_dev_name.
Assisted-by: llama.cpp:local pi
Add graphs reused counter to the per-slot timing output, printed via
llama_perf_context().
Assisted-by: llama.cpp:local pi
Co-authored-by: ggerganov <ggerganov@users.noreply.github.com>
* 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 <ggerganov@users.noreply.github.com>
* llama-eval : add per-problem summary table to HTML reports
- Add chunk_idx and problem_idx to TaskState and saved case dicts
- Group completed cases by problem_idx in dump_html()
- Render per-problem summary table before individual task table
- Columns: Problem (zero-padded), Runs, Correct (n/r),
Tokens (min/avg/max), T/s (min/avg/max), Gen s (min/avg/max)
- Sorted by problem index, monospace font, right-aligned numbers
- Colspan headers for grouped stats, auto width
- Simulator: add /v1/models endpoint, timings in response,
template-aware question matching, --dataset arg (aime/aime2025)
Assisted-by: llama.cpp:local pi
* llama-eval : add tabs for Detailed and Summary tables, apply monospace font globally
- Wrap Detailed and Summary tables in switchable tabs (Detailed active by default)
- Remove summary-section wrapper, use tab labels instead
- Apply monospace font to all tables and the top bar
Assisted-by: llama.cpp:local pi
* llama-eval : redesign top bar as CSS grid label/value pairs
- Replace flat span list with 4-column grid layout (2 pairs per row)
- Labels in muted color (#888), values in dark (#222)
- Bold dataset name and model name
- Removed media query, always uses 4 columns
Assisted-by: llama.cpp:local pi
* llama-eval : use realistic token counts and throughput in simulator
- comp_tokens: [30, 80] → [10000, 60000]
- tps_gen: derived → uniform [90.0, 110.0]
- t_gen_ms: now computed from tokens/tps
Assisted-by: llama.cpp:local pi
* llama-eval : color Answer column green/red based on correctness
Use the same .correct/.incorrect CSS classes on the Answer column
to make correct answers green and incorrect answers red.
Assisted-by: llama.cpp:local pi
* llama-eval : fix pyright errors from max(..., key=len) type inference
Use key=lambda x: len(x) instead of key=len so the type checker
infers the return type as str instead of Sized, fixing:
- unresolved-attribute: Object of type Sized has no attribute lower
- not-subscriptable: Cannot subscript object of type Sized
Assisted-by: llama.cpp:local pi
Add Aime2026Dataset class loading from MathArena/aime_2026 on
HuggingFace. 30 problems (two sets of 15), single config/split.
Usage: --dataset aime2026
Assisted-by: llama.cpp:local pi
* working llama-eval mc and math suite
* multi source llama-eval
* Add readme
* add checkpointing
* examples: add llama-server simulator for testing eval scripts
Add a standalone Python script that simulates a llama-server HTTP endpoint
for testing the eval script. The simulator:
- Implements /v1/chat/completions endpoint with OpenAI-compatible format
- Loads AIME dataset from HuggingFace with local caching
- Uses Levenshtein distance for intelligent question matching
- Supports configurable success rate for correct/wrong answer generation
- Provides debug logging for troubleshooting
Also includes test scripts and documentation for testing and understanding
the simulator functionality.
* examples: refactor test-simulator.sh for better readability
Extract repeating question string into TEST_QUESTION variable and
create make_request() helper function to reduce code duplication.
Add proper error handling for error responses.
* docs: update llama-eval-discussion.md with session work summary
Add summary of llama-server-simulator implementation work including
features, testing results, technical decisions, and refactoring.
* examples: add simplified llama-eval-new.py for AIME evaluation
- Create new simplified evaluation script focused only on AIME
- Implement EvalState and Processor dataclasses for structured state management
- Add real-time feedback showing correct/incorrect status per case
- Abstract grading interface for external grader support
- Use structured JSON output for eval state
- Apply HuggingFace dataset caching to avoid repeated downloads
- Remove Levenshtein matching - eval script only sends requests and validates answers
* docs: remove README.md from llama-eval
* examples: implement flexible grader system for answer validation
- Add Grader class supporting regex and CLI-based grading
- Implement built-in regex patterns for AIME, GSM8K, MMLU, HellaSwag, ARC, WinoGrande
- Add CLI grader interface: python script.py --answer <pred> --expected <gold>
- Add HF telemetry disable to avoid warnings
- Support exact match requirement for regex patterns
- Add 30-second timeout for CLI grader
- Handle both boxed and plain text formats for AIME answers
* examples: use HF_HUB_OFFLINE to avoid HF Hub warnings
* examples: remove HF_HUB_OFFLINE to allow dataset download
* examples: use cached dataset path to avoid HF Hub requests
* examples: use cached dataset path in simulator to avoid HF Hub requests
* docs: update llama-eval-discussion.md with session work summary
* examples: add threading support and model parameter to llama-eval-new.py
- Add ThreadPoolExecutor for parallel request processing controlled by --threads
- Add --model argument to specify model name in request data
- Refactor process() to use thread-safe _process_single_case() method
- Update progress tracking to work with concurrent execution
* docs: update llama-eval-discussion.md with threading and model parameter updates
- Add threading support implementation details
- Document ThreadPoolExecutor usage and thread safety
- Add model parameter implementation details
- Include testing results for both features
* examples: add task summary table to llama-eval-new.py
* eval : print progress
* eval : add prompts
* test : fix path
* sim : fix answer matching
* eval : support multiple dataset runs
* minor
* improve grader
* docs
* remove old files
* datasets : add gsm8k
* add gpqa + sampling + docs
* rename
* grader : improve example answers
* cont
* datasets : add aime2025
* grader : update prompt
* grade : improve regex + logs
* datasets : fix aime2025
* cleanup
* add AGENTS.md
* ignore errors
* resume eval
* cleanup
* fix counts
* simplify
* fix prompts
* add html
* store full response
* add tokens
* resoning and error handling
* refactor
* track total time
* remove junk
* eval : unify "judge" terminology to "grader"
Replace all occurrences of "judge" with "grader" for consistency
across the codebase (CLI args, Grader class fields, help text).
Assisted-by: llama.cpp:local pi
* eval : add Wilson score confidence interval to results
Compute 95% CI on-the-fly from completed cases. Displayed in
terminal output, HTML report, and JSON state.
* llama-eval : add per-task generation speed from server timings
Extract predicted_per_second from the server timings response and store
it as tps_gen per task. Display in console progress, print_all_tasks,
and HTML report.
Assisted-by: llama.cpp:local pi
* llama-eval : add per-task generation time from server timings
Extract predicted_ms from the server timings response and store it as
t_gen_ms per task. Display in seconds with one decimal digit in console
progress, print_all_tasks, and HTML report.
Assisted-by: llama.cpp:local pi
* llama-eval : rename display, escaped, and count variables to use prefix convention
- _display suffix → display_ prefix (answer, tokens, tps, t_gen)
- _escaped suffix → escaped_ prefix (response, prompt, reasoning)
- _count suffix → n_ prefix (correct, incorrect, pending)
Assisted-by: llama.cpp:local pi
* llama-eval : support multiple evaluation endpoints with dynamic task distribution
- Add ServerConfig dataclass (url, threads, name)
- Accept comma-separated --server, --threads, --server-name CLI args
- Dynamic shared-queue task distribution across servers (fast servers do more work)
- One ThreadPoolExecutor per server, workers pull from shared Queue
- Track which server processed each task (server_name in results)
- Thread-safe EvalState with threading.Lock for concurrent mutations
- Server column in HTML report and console output
- Backward compatible: single server works as before
Assisted-by: llama.cpp:local pi
* llama-server-simulator : replace Flask with stdlib http.server
- Use HTTPServer + BaseHTTPRequestHandler instead of Flask
- RequestHandler handles POST /v1/chat/completions
- Server runs in daemon thread with clean Ctrl+C shutdown
- Remove flask and unused asdict imports
Assisted-by: llama.cpp:local pi
* llama-eval : update README with PR link and quick-start examples
Assisted-by: llama.cpp:local pi
* llama-eval : track model name in eval state and verify on resume
- Store model_name in EvalState and JSON output
- Display model in HTML summary table
- Verify --model matches stored model when resuming
Assisted-by: llama.cpp:local pi
* llama-server-simulator : fix comment - Dice coefficient, not Levenshtein
Assisted-by: llama.cpp:local pi
* llama-eval : require --grader-model or --model when using --grader-type llm
Assisted-by: llama.cpp:local pi
* llama-eval : protect dump() with lock for thread safety
Assisted-by: llama.cpp:local pi
* llama-eval : compact HTML report output
- Replace verbose summary table with single inline bar
- Shorten status text: '✓'/'✗'/'–'/'!' instead of full words
- Flatten CSS: remove box-shadows, border-radius, reduce padding
- Use system-ui font, 13px table, 12px details
- Conditional reasoning section (only shown when present)
- Single toggle JS function instead of two
- Shorter column headers
Assisted-by: llama.cpp:local pi
* llama-eval : check server connectivity on startup
- Hit /v1/models for each server before evaluation
- Exit with error if any server is unreachable
- Print comma-separated model IDs per server in startup output
- Sequential checks, no retries, no timeout override
Assisted-by: llama.cpp:local pi
* llama-eval : use server1/server2 instead of gpu1/gpu2 in README
Assisted-by: llama.cpp:local pi
---------
Co-authored-by: gatbontonpc <gatbontonpc@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>
Georgi Gerganov