Jeff Bolz [Sat, 27 Sep 2025 10:36:11 +0000 (06:36 -0400)]
vulkan: support GET_ROWS for k-quants (#16235)
The dequantize functions are copy/pasted from mul_mm_funcs.comp with very few
changes - add a_offset and divide iqs by 2. It's probably possible to call
these functions from mul_mm_funcs and avoid the duplication, but I didn't go
that far in this change.
model : make minicpm embedding_scale, residual_scale and logit_scale optional with legacy defaults (#16273)
* minicpm: make GGUF scaling keys optional with legacy defaults
Older MiniCPM GGUFs do not include the scaling metadata keys (minicpm.embedding_scale, minicpm.residual_scale, minicpm.logit_scale). The loader currently treats these as required, so quantization fails with:
key not found in model: minicpm.embedding_scale
This change restores backward compatibility by treating these keys as optional in the loader and using the older MiniCPM scaling values:
When the GGUF provides the keys, their values override the defaults; otherwise the legacy defaults are used. Newer GGUFs that already include these keys are unaffected.
Signed-off-by: Aaron Teo <redacted>
* devops: fix test does not exist
Signed-off-by: Aaron Teo <redacted>
* devops: fix model not found llama-eval-callback
Signed-off-by: Aaron Teo <redacted>
* Fix q3_K dot product error in test-quantize-fns on s390x
Array q8bytes had only 4 elements allocated, but 8 elements accessed.
This lead to write out of bounds and later read of overwritten values out of bounds
and incorrect result.
Signed-off-by: Aaron Teo <redacted>
* devops: re-enable ppc64le for testing
Signed-off-by: Aaron Teo <redacted>
* devops: activate test-thread-safety for s390x
Aleksander Grygier [Fri, 26 Sep 2025 16:35:42 +0000 (18:35 +0200)]
Allow viewing conversations even when llama server is down (#16255)
* webui: allow viewing conversations and sending messages even if llama-server is down
- Cached llama.cpp server properties in browser localStorage on startup, persisting successful fetches and reloading them when refresh attempts fail so the chat UI continues to render while the backend is unavailable.
- Cleared the stored server properties when resetting the store to prevent stale capability data after cache-backed operation.
- Kept the original error-splash behavior when no cached props exist so fresh installs still surface a clear failure state instead of rendering stale data.
* webui: extend cached props fallback to offline errors
Treat connection failures (refused, DNS, timeout, fetch) the same way as
server 5xx so the warning banner shows up when cache is available, instead
of falling back to a full error screen.
* webui: Left the chat form enabled when a server warning is present so operators can keep sending messages
e.g., to restart the backend over llama-swap, even while cached /props data is in use
common : use cpp-httplib as a cURL alternative for downloads (#16185)
* vendor : update httplib
Signed-off-by: Adrien Gallouët <redacted>
* common : use cpp-httplib as a cURL alternative for downloads
The existing cURL implementation is intentionally left untouched to
prevent any regressions and to allow for safe, side-by-side testing by
toggling the `LLAMA_CURL` CMake option.
Signed-off-by: Adrien Gallouët <redacted>
* ggml : Bump to Windows 10
ci : create git tags for released docker images (#16008)
* ci : create git tags for released docker images
When releasing a docker image for build number X, we should also create
the corresponding git tag. This allows users to easily checkout the
corresponding source tree for given docker image.
Aman Gupta [Thu, 25 Sep 2025 14:35:05 +0000 (22:35 +0800)]
CUDA: add a fused top-K MoE kernel (#16130)
* CUDA: add a fused top-K MoE kernel
This kernel does the following:
1. softmax over the logits per token [n_experts, n_tokens]
2. argmax reduce over the top-k (n_experts_used) logits
3. write weights + ids to global memory
It is intended as fusion of softmax->top-k->get_rows pipeline for MoE models
* Refactor into ggml_cuda_should_use_topk_moe
* Review: Use better coalescing pattern, use WARP_SIZE, store logits into registers before
Daniel Bevenius [Thu, 25 Sep 2025 10:02:36 +0000 (12:02 +0200)]
model-conversion : add embedding prompt file support (#15871)
This commit adds support for passing a prompt file to the model
conversion targets/scripts. It also updates the logits.cpp to print out
embedding information in the same format as when running the original
embedding model.
The motivation for this is that it allows us to pass files of different
sizes when running the converted models and validating the logits.
This can be particularly important when testing the sliding window
functionality of models where the sequence length needs to exceed a
certain number of tokens to trigger the sliding window logic.
Daniel Bevenius [Thu, 25 Sep 2025 09:36:47 +0000 (11:36 +0200)]
server : add support for external server for tests (#16243)
This commit adds support for using an externally started llama-server
instance for the server tests. This can be enabled by setting the
DEBUG_EXTERNAL environment variable.
The motivation for this is to allow debugging of the server itself
when investigating a test failure. Instructions for how to do this are
added to the README.md file in the tests directory.
Use RPC_DEBUG environment variable to enable debug messages.
Add helper macro LOG_DBG() which does an early
check of the env var before calling GGML_LOG_DEBUG().
Make sure we log a debug message for every server function.
ggml : split graph allocations according to backend max buffer size (#15815)
* ggml : make gallocr respect the backend's max buffer size
* if the graph requires more memory than can fit into a single allocation, split it into multiple backend buffers
* vulkan: report the actual max allocation size in buffer type interface
* fix missing newline, apple-clang warning
* track size of individual chunks in ggml_dyn_tallocr and raise max chunks.
revert to use suballocation_block_size as max chunk size for vulkan.
* track (chunk, offset) pairs instead of "global" offsets through gallocr.
* simpler, don't need loops to map between local/global offsets
* touches more code
* fix dyn_tallocr_max_size and initialization
* fix memory leak when buffers are reused due to same buffer type appearing multiple times
* make vbuffer allocation follow the same logic as backend_buffer did before
* continue to use leftover unallocated space of previous chunks after a new one has been created
* treat free blocks of each chunk as separate list
* they're still allocated together, but start/end of each chunk is tracked, and allocate/free iterate over sub-ranges
* exhaust freed blocks of all chunks before considering their last blocks with unallocated space
* start with 0 chunks/blocks and create chunks as needed
* allow the last chunk to grow beyond max size
* refactor: move adding new free block and new chunk into separate functions
* allocate chunks individually with a separate free-blocks list for each one
* needs a bit more memory/allocations/indirections, but code is simpler
Gabe Goodhart [Mon, 22 Sep 2025 18:40:10 +0000 (12:40 -0600)]
feat: Add conversion support in GraniteHybrid for non-hybrid (all attn) (#16177)
This is a configuration of the hparams in the GraniteHybrid architecture
that devolves to the Granite (or GraniteMoe) architecture (ie Granite 3.x).
It may be used for some models in the Granite 4 family with the
GraniteHybrid architecture acting as a superset arch. Rather than support
it directly in the c++ graph, we simply coerce the architecture flag back
to the correct "granite" or "granitemoe" architecture.
Branch: gabe-l-hart/GraniteNonHybridConversion
Signed-off-by: Gabe Goodhart <redacted> Co-authored-by: Sigbjørn Skjæret <redacted>
Haiyue Wang [Mon, 22 Sep 2025 17:57:46 +0000 (01:57 +0800)]
clang-tidy : disable warning about performance enum size (#16127)
Disable 'performance-enum-size' checking:
Enum 'llama_token_type' uses a larger base type ('unsigned int', size: 4 bytes)
than necessary for its value set, consider using 'std::uint8_t' (1 byte) as the
base type to reduce its size.
Daniel Bevenius [Tue, 16 Sep 2025 04:16:52 +0000 (06:16 +0200)]
ggml : introduce semantic versioning (ggml/1336)
* ggml : introduce semantic versioning
This commit introduces semantic versioning for the GGML library.
The motivation for this is that the current versioning, using build
numbers, makes it difficult to track changes and releases for projects
that use ggml.
The release steps are the following:
1. Sync the changes from llama.cpp using sync-llama-am.sh and after the
PR has been approved and merged move to step 2.
2. Run scripts/release.sh and specify the type of release, major, minor,
or patch. This script will handle incrementing the version
(major|minor|patch), create a new commit with the version change,
create a tag for the version, and prepare for the next development
iteration.
3. Inspect the commits/tag and push to master. This will trigger the
github release workflow which is triggered for new tags which will
then publish a new release on github.
Example usage:
```console
$ ./scripts/release.sh major --dry-run
[dry-run] - No changes will be made
Step 1: Reading current version...
Current version: 0.9.0-dev
New release version: 1.0.0
Step 2: Updating version in ggml/CMakeLists.txt...
[dry-run] Would update GGML_VERSION_MAJOR to 1
[dry-run] Would update GGML_VERSION_MINOR to 0
[dry-run] Would update GGML_VERSION_PATCH to 0
[dry-run] Would remove -dev suffix
Step 3: Committing version bump...
[dry-run] Would commit: 'ggml : bump version to 1.0.0'
Step 4: Creating git tag...
[dry-run] Would create tag: v1.0.0 with message 'Release version 1.0.0'
Step 5: Preparing for next development cycle...
[dry-run] Would update GGML_VERSION_MINOR to 1
[dry-run] Would add -dev suffix back
Step 6: Committing development version...
[dry-run] Would commit: 'ggml : prepare for development of 1.1.0-dev'
[dry-run] Summary (no changes were made):
• Would have released version: 1.0.0
• Would have created tag: v1.0.0
• Would have set next development version: 1.1.0-dev
```
llama-bench: add --devices and --list-devices support (#16039)
* * llama-bench: add --devices support
- Support --devices same as llama-server
- Provide for benchmarking different device combinations
- Include --list-devices like llama-server for convenience
* fix: field display ordering restored
* fix: integrated the rpc devices
- aimed to mimic the server as much as possible
* cleanup: defaults for list-devices
- handle dup device listing with RPC
* cleanup: remove dup device load calls
* docs: update llama-bench
- added the recently added n-cpu-moe option to the docs while in there
* llama-bench: rpc device simplification
* rpc servers unify with other devices earlier, simplifying code
* --list-devices made stateless and simpler
* various cleanup
cmake : fix static linking for OpenMP on Unix-like systems (#16031)
When compiling with GGML_STATIC=ON, the build process would produce a
binary that was still dynamically linked to OpenMP. This defeats the
purpose of a static build:
This commit resolves the issue by modifying `CMAKE_FIND_LIBRARY_SUFFIXES`
to prioritize `.a` files, forcing CMake to link the static version of
the library.
Eric Curtin [Thu, 18 Sep 2025 15:22:50 +0000 (16:22 +0100)]
Add resumable downloads for llama-server model loading (#15963)
- Implement resumable downloads in common_download_file_single function
- Add detection of partial download files (.downloadInProgress)
- Check server support for HTTP Range requests via Accept-Ranges header
- Implement HTTP Range request with "bytes=<start>-" header
- Open files in append mode when resuming vs create mode for new downloads
server : include usage statistics only when user request them (#16052)
* server : include usage statistics only when user request them
When serving the OpenAI compatible API, we should check if
{"stream_options": {"include_usage": true} is set in the request when
deciding whether we should send usage statistics
overview / pkg / ggml / sources / llama.cpp / log