c5897995a7
mtmd : chat : Fix extra \n between text and media marker ( #19595 )
...
* mtmd : chat : Fix extra \n between text and media marker
Thanks to @tugot17 for detecting and reporting the issue.
For vision models (e.g. LFM2.5-VL-1.6B and Qwen/Qwen3-VL-4B-Instruct) `llama-mtmd-cli` produces identical output to HF implementation.
However `llama-server` doesn't. I traced it down to extra newline
inserted after `<__media__>`.
This happens in `to_json_oaicompat`, that treats media markers as text
and joins all parts with `\n` separator.
PR introduces new type `media_marker` and uses it for media markers.
Extra logic is added to prevent insertion of newlines before and after
media markers.
With this change number of input tokens is identical to HF
implementation and as a result the output is also identical.
I explored other ways to address the issue
* remove completely `\n` between text parts in `to_json_oaicompat`
* merge text messages in server-common.cpp before sending them to `to_json_oaicompat`
Please propose alternative ways of fixing this issue.
* Refactor to use explicite per type ifs
* Update common/chat.cpp
Co-authored-by: Piotr Wilkin (ilintar) <piotr.wilkin@syndatis.com >
* Update common_chat_templates_apply_legacy
---------
Co-authored-by: Piotr Wilkin (ilintar) <piotr.wilkin@syndatis.com >
2026-02-19 12:18:57 +01:00
8a70973557
Add Jinja support for "indent" string filter ( #19529 )
...
* Add partial Jinja support for "indent" string filter
* Fully implement indent
* Add tests for all width variants.
* Update tests/test-jinja.cpp
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com >
* Fix getline ignoring trailing newlines
* Update common/jinja/value.cpp
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com >
* fix first indent condition
---------
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com >
2026-02-19 00:25:52 +01:00
a569bda445
common : make small string helpers as inline functions ( #19693 )
...
Also use string_view when it make sense and fix some corner cases.
Signed-off-by: Adrien Gallouët <angt@huggingface.co >
2026-02-18 08:03:01 +01:00
b6bb9c914e
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/workflows/winget.yml
# CMakeLists.txt
# common/CMakeLists.txt
# examples/model-conversion/scripts/causal/run-org-model.py
# ggml/src/ggml-cpu/CMakeLists.txt
# tools/perplexity/perplexity.cpp
# tools/server/CMakeLists.txt
2026-02-17 19:41:28 +08:00
65cede7c70
build : cleanup library linking logic ( #19665 )
...
Signed-off-by: Adrien Gallouët <angt@huggingface.co >
2026-02-17 08:36:45 +01:00
cceb1b4e33
common : inline functions ( #18639 )
2026-02-16 17:52:24 +02:00
8d61ff4530
revert "build : remove LLAMA_HTTPLIB option ( #19623 )"
2026-02-16 18:32:29 +08:00
dbe0604dfc
tools broken currently
2026-02-16 18:10:42 +08:00
72f7e01b27
Merge commit '01d8eaa28d57bfc6d06e30072085ed0ef12e06c5' into concedo_experimental
...
# Conflicts:
# build-xcframework.sh
# scripts/sync_vendor.py
# tests/test-backend-ops.cpp
# tools/mtmd/CMakeLists.txt
# tools/rpc/rpc-server.cpp
2026-02-16 15:36:59 +08:00
9e118b97c4
build : remove LLAMA_HTTPLIB option ( #19623 )
...
This option was introduced as a workaround because cpp-httplib could not
build on visionOS. Since it has been fixed and now compiles on all platforms,
we can remove it and simplify many things.
Signed-off-by: Adrien Gallouët <angt@huggingface.co >
2026-02-15 15:38:50 +01:00
badba89320
NetBSD build support ( #19589 )
2026-02-14 09:47:01 +01:00
2d8015e8a4
llama : update LoRA API. + fix excessive graph reserves ( #19280 )
...
* Refactoring to use new llama_put_adapter_loras
* cont : alternative lora API
---------
Co-authored-by: Jake Chavis <jakechavis6@gmail.com >
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
2026-02-14 10:06:27 +02:00
45dc155530
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/ISSUE_TEMPLATE/010-bug-compilation.yml
# .github/ISSUE_TEMPLATE/011-bug-results.yml
# AGENTS.md
# SECURITY.md
# ggml/src/ggml-hexagon/htp/flash-attn-ops.c
# ggml/src/ggml-hexagon/htp/main.c
# ggml/src/ggml-opencl/CMakeLists.txt
# ggml/src/ggml-opencl/ggml-opencl.cpp
# ggml/src/ggml-opencl/kernels/cvt.cl
# scripts/sync_vendor.py
# src/unicode.cpp
# tests/test-backend-ops.cpp
# tools/cli/cli.cpp
2026-02-14 12:44:16 +08:00
b48e80f677
common : update download code ( #19573 )
...
* common : remove legacy .json to .etag migration code
Signed-off-by: Adrien Gallouët <angt@huggingface.co >
* common : simplify common_download_file_single_online
This commit also force a redownload if the file exists
but has no .etag file.
Signed-off-by: Adrien Gallouët <angt@huggingface.co >
---------
Signed-off-by: Adrien Gallouët <angt@huggingface.co >
2026-02-13 15:10:46 +01:00
bff3fd3e34
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# common/common.cpp
# docs/backend/snapdragon/README.md
# ggml/src/ggml-hexagon/htp/htp-ops.h
# ggml/src/ggml-hexagon/htp/matmul-ops.c
# ggml/src/ggml-opencl/CMakeLists.txt
# ggml/src/ggml-opencl/ggml-opencl.cpp
# scripts/pr2wt.sh
# tests/test-backend-ops.cpp
# tools/server/README.md
2026-02-13 14:00:45 +08:00
55524e160b
temp merge, not working
2026-02-13 12:11:26 +08:00
338085c69e
args : add -kvu to llama-parallel ( #19577 )
2026-02-12 21:52:41 +02:00
261d78eaaa
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# CMakeLists.txt
# README.md
# docs/speculative.md
# ggml/src/ggml-cann/aclnn_ops.cpp
# ggml/src/ggml-cann/ggml-cann.cpp
# tests/CMakeLists.txt
# tests/test-backend-ops.cpp
# tools/mtmd/clip.cpp
2026-02-12 18:05:20 +08:00
4ae1b7517a
common : replace deprecated codecvt using parse_utf8_codepoint ( #19517 )
...
Signed-off-by: Adrien Gallouët <adrien@gallouet.fr >
2026-02-12 07:27:52 +01:00
3136a849db
common : remove unused token util functions ( #19506 )
...
This commit removes two unused functions `common_lcp` and `common_lcs`.
The last usage of these functions was removed in
Commit 33eff40240
2026-02-11 17:41:35 +01:00
0c1f39a9ae
common : improve download error reporting ( #19491 )
...
Signed-off-by: Adrien Gallouët <angt@huggingface.co >
2026-02-11 09:27:55 +01:00
8ee538ce73
llama : correct typos 'occured' and 'occurences' ( #19414 )
...
Co-authored-by: thecaptain789 <thecaptain789@users.noreply.github.com >
2026-02-11 07:05:31 +01:00
98e57ca422
chat: fix case where template accepts type content only ( #19419 )
...
* chat: fix case where template accepts type content only
* rm stray log
* reuse render_message_to_json
2026-02-09 22:14:12 +01:00
292f6908cd
spec : remove check rate ( #19377 )
...
* spec: remove parameter spec-ngram-check-rate
* spec : renamed statistics vars
* spec : add n_call_begin, n_call_accept
* spec : don't enable key-map-stats
2026-02-09 15:30:50 +02:00
a0a78dacc4
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/workflows/build.yml
# docs/ops.md
# docs/ops/SYCL.csv
# ggml/src/ggml-sycl/element_wise.cpp
# ggml/src/ggml-sycl/ggml-sycl.cpp
# ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
# ggml/src/ggml-webgpu/ggml-webgpu.cpp
# pyproject.toml
# requirements/requirements-convert_legacy_llama.txt
# src/CMakeLists.txt
# src/llama-vocab.cpp
# tests/test-backend-ops.cpp
2026-02-07 15:54:02 +08:00
dfde5993ea
common : add common_speculative_is_compat() ( #19270 )
...
* llama : add llama_memory_can_rm_suffix()
* Revert "llama : add llama_memory_can_rm_suffix()"
This reverts commit d30e59b62a15ef4266a6503e3f4eba770aec001b.
* spec : check if the target context is compatible for spec decoding
2026-02-06 16:47:22 +02:00
157fac7bd0
Merge commit 'c342c3b93de358a4571941b41c35dc5ba2081145' into concedo_experimental
...
# Conflicts:
# .github/workflows/build.yml
# CODEOWNERS
# scripts/sync_vendor.py
2026-02-05 22:23:05 +08:00
e0c93af2a0
debug: make common_debug_print_tensor readable ( #19331 )
...
* debug: make common_debug_print_tensor readable
* editorconfig
2026-02-04 17:55:31 +01:00
1a36ef20c3
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# tests/test-backend-ops.cpp
2026-02-04 20:53:35 +08:00
d838c22bb3
spec : fix the check-rate logic of ngram-simple ( #19261 )
...
* spec : fix the check-rate logic of ngram-simple
* cont : refactor + fix checks
2026-02-04 10:39:53 +02:00
7b393fa487
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/workflows/build.yml
# AUTHORS
# ci/run.sh
# docs/backend/SYCL.md
# docs/build.md
# docs/multimodal/minicpmo2.6.md
# docs/multimodal/minicpmo4.0.md
# docs/multimodal/minicpmv2.5.md
# docs/multimodal/minicpmv2.6.md
# docs/multimodal/minicpmv4.0.md
# docs/multimodal/minicpmv4.5.md
# docs/ops.md
# docs/ops/SYCL.csv
# docs/speculative.md
# examples/deprecation-warning/README.md
# examples/deprecation-warning/deprecation-warning.cpp
# examples/model-conversion/Makefile
# examples/model-conversion/scripts/causal/convert-model.sh
# ggml/include/ggml-cann.h
# ggml/src/ggml-cann/acl_tensor.cpp
# ggml/src/ggml-cann/acl_tensor.h
# ggml/src/ggml-cann/aclnn_ops.cpp
# ggml/src/ggml-cann/aclnn_ops.h
# ggml/src/ggml-cann/common.h
# ggml/src/ggml-cann/ggml-cann.cpp
# ggml/src/ggml-metal/CMakeLists.txt
# ggml/src/ggml-opencl/ggml-opencl.cpp
# ggml/src/ggml-opencl/kernels/concat.cl
# ggml/src/ggml-opencl/kernels/repeat.cl
# ggml/src/ggml-opencl/kernels/scale.cl
# ggml/src/ggml-opencl/kernels/tanh.cl
# ggml/src/ggml-sycl/CMakeLists.txt
# ggml/src/ggml-sycl/dpct/helper.hpp
# ggml/src/ggml-sycl/ggml-sycl.cpp
# ggml/src/ggml-sycl/outprod.cpp
# ggml/src/ggml-sycl/rope.cpp
# ggml/src/ggml-sycl/wkv.cpp
# src/llama-vocab.cpp
# tests/test-autorelease.cpp
# tests/test-backend-ops.cpp
# tools/cvector-generator/pca.hpp
# tools/export-lora/export-lora.cpp
# tools/perplexity/README.md
2026-02-03 19:00:42 +08:00
aeb827a3cc
spec : simplify time measurement using common_time_meas ( #19262 )
2026-02-03 08:20:15 +02:00
0dfcd3b607
jinja : add missing 'in' test to template engine ( #19004 ) ( #19239 )
...
* jinja : add missing 'in' test to template engine (#19004 )
The jinja template parser was missing the 'in' test from
global_builtins(), causing templates using reject("in", ...),
select("in", ...), or 'x is in(y)' to fail with
"selectattr: unknown test 'in'".
This broke tool-calling for Qwen3-Coder and any other model
whose chat template uses the 'in' test.
Added test_is_in supporting array, string, and object containment
checks, mirroring the existing 'in' operator logic in runtime.cpp.
Includes test cases for all three containment types plus
reject/select filter usage.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
* reuse test_is_in in binary op
---------
Co-authored-by: Sid Mohan <sidmohan0@users.noreply.github.com >
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com >
Co-authored-by: Xuan Son Nguyen <son@huggingface.co >
2026-02-02 21:00:55 +01:00
b4d05a3d2f
spec : various improvements ton ngram-map + docs ( #19253 )
...
* spec: ngram-map and reasoning chats
* spec: add t_begin and t_accept
* ngram-map : add internal hash map
* docs : update ngram-map, add ngram-mod
* docs : fix ngram-map-k
* docs : differences between implementations
2026-02-02 08:26:58 +02:00
ddce19db72
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .devops/nix/package-gguf-py.nix
# .devops/nix/scope.nix
# common/CMakeLists.txt
# docs/backend/SYCL.md
# examples/lookahead/lookahead.cpp
# examples/lookup/lookup.cpp
# examples/sycl/run-llama2.sh
# examples/sycl/win-run-llama2.bat
# examples/sycl/win-test.bat
# ggml/src/ggml-hexagon/CMakeLists.txt
# ggml/src/ggml-hexagon/htp/flash-attn-ops.c
# ggml/src/ggml-hexagon/htp/hvx-dump.h
# ggml/src/ggml-hexagon/htp/hvx-reduce.h
# ggml/src/ggml-hexagon/htp/matmul-ops.c
# ggml/src/ggml-hexagon/htp/softmax-ops.c
# ggml/src/ggml-hexagon/htp/unary-ops.c
# ggml/src/ggml-opencl/CMakeLists.txt
# ggml/src/ggml-opencl/ggml-opencl.cpp
# ggml/src/ggml-opencl/kernels/cvt.cl
# scripts/sync-ggml.last
2026-02-01 22:35:25 +08:00
4927795810
ngram-mod : fix build [no ci] ( #19216 )
2026-01-30 21:27:27 +02:00
dabaa2e77a
spec : add ngram-mod ( #19164 )
...
* spec : add ngram-mod
* cont : simplify + keep track of occupancy
* cont : cleanup
* cont : move initialization to common/speculative
* cont : cleanup
* cont : cleanup
* cont : fix
2026-01-30 18:21:48 +02:00
2e916f996a
jinja : add unordered_map include to value.h [no ci] ( #19205 )
...
On macos Sequoia 15.7.3, x86_64, the build has recently started failing with
```
In file included from .../code/cpp/llama.cpp/common/jinja/string.cpp:2:
.../code/cpp/llama.cpp/common/./jinja/value.h:478:10: error: no template named 'unordered_map' in namespace 'std'
478 | std::unordered_map<value, value, value_hasher, value_equivalence> unordered;
| ~~~~~^
In file included from .../code/cpp/llama.cpp/common/jinja/caps.cpp:1:
.../code/cpp/llama.cpp/common/jinja/value.h:478:10: error: no template named 'unordered_map' in namespace 'std'
478 | std::unordered_map<value, value, value_hasher, value_equivalence> unordered;
| ~~~~~^
In file included from .../code/cpp/llama.cpp/common/jinja/value.cpp:1:
In file included from .../code/cpp/llama.cpp/common/jinja/runtime.h:4:
.../code/cpp/llama.cpp/common/jinja/value.h:478:10: error: no template named 'unordered_map' in namespace 'std'
478 | std::unordered_map<value, value, value_hasher, value_equivalence> unordered;
[...]
```
After a bit of digging to make sure all the appropriate flags were used, I notifced that the necessary header was not included. This fixes the build for me and should not affect negatively other builds that for some reasons were already succeeding
2026-01-30 16:09:44 +01:00
8d173f50c2
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/workflows/build.yml
# docs/backend/SYCL.md
# docs/backend/snapdragon/CMakeUserPresets.json
# docs/backend/snapdragon/README.md
# docs/backend/snapdragon/developer.md
# docs/ops.md
# docs/ops/SYCL.csv
# embd_res/templates/upstage-Solar-Open-100B.jinja
# ggml/src/CMakeLists.txt
# ggml/src/ggml-hexagon/CMakeLists.txt
# ggml/src/ggml-hexagon/ggml-hexagon.cpp
# ggml/src/ggml-sycl/element_wise.cpp
# ggml/src/ggml-sycl/element_wise.hpp
# ggml/src/ggml-sycl/ggml-sycl.cpp
# ggml/src/ggml-webgpu/wgsl-shaders/flash_attn.wgsl
# tests/test-chat.cpp
2026-01-30 15:32:59 +08:00
7b7ae857f6
chat : add parsing for solar-open-100b ( #18540 )
...
* chat : add parsing for solar-open-100b
* add comments to rules
* cont : make assistant start optional
* cont : remove assistant start prefix altogether
---------
Co-authored-by: Piotr Wilkin (ilintar) <piotr.wilkin@syndatis.com >
2026-01-29 16:06:15 +01:00
7e755014b2
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/workflows/winget.yml
# CODEOWNERS
# common/CMakeLists.txt
# common/arg.cpp
# docs/ops/SYCL.csv
# examples/lookup/lookup-create.cpp
# examples/lookup/lookup-stats.cpp
# examples/lookup/lookup.cpp
# examples/speculative-simple/speculative-simple.cpp
# examples/speculative/speculative.cpp
# ggml/src/ggml-hip/CMakeLists.txt
# ggml/src/ggml-sycl/dpct/helper.hpp
# ggml/src/ggml-sycl/ggml-sycl.cpp
# ggml/src/ggml-sycl/norm.cpp
# ggml/src/ggml-zendnn/ggml-zendnn.cpp
# tests/test-chat-template.cpp
2026-01-29 23:05:05 +08:00
46cd17c17e
Merge commit '88d23ad515e60c64db8df22b3de23cba00d044ab' into concedo_experimental
...
# Conflicts:
# CODEOWNERS
# docs/build.md
# ggml/CMakeLists.txt
# ggml/src/CMakeLists.txt
# ggml/src/ggml-webgpu/ggml-webgpu.cpp
# ggml/src/ggml-zendnn/CMakeLists.txt
# tests/test-chat-template.cpp
2026-01-29 22:25:56 +08:00
b45ef2702c
jinja : do not pass empty tools and add some none filters ( #19176 )
Python Type-Check / pyright type-check (push) Failing after 38s
Check Pre-Tokenizer Hashes / pre-tokenizer-hashes (push) Has been cancelled
Python check requirements.txt / check-requirements (push) Has been cancelled
Update Operations Documentation / update-ops-docs (push) Has been cancelled
2026-01-29 14:06:54 +01:00
eed25bc6b0
arg : add -kvu to llama-batched-bench ( #19172 )
2026-01-29 08:50:47 +02:00
72d3b1898a
spec : add self‑speculative decoding (no draft model required) + refactor ( #18471 )
...
* server: introduce self-speculative decoding
* server: moved self-call into speculative.cpp
* can_speculate() includes self-speculation
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
* server: can_speculate() tests self-spec
* server: replace can_speculate() with slot.can_speculate()
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com >
* common: use %zu format specifier for size_t in logging
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com >
* server: can_speculate() requires a task instance
* common: ngram map, config self-speculative decoding
* common: add enum common_speculative_type
* common: add vector of speculative states
* common: add option --spec-draftless
* server: cleanup (remove slot.batch_spec, rename)
* common: moved self-spec impl to ngram-map
* common: cleanup (use common_speculative_state_draft)
* spec : refactor
* cont : naming
* spec: remove --spec-config
* doc: (draftless) speculative decoding
* common: print performance in spec decoding
* minor : cleanup
* common : better names
* minor : cleanup + fix build
* minor: comments
* CODEOWNERS: add common/ngram-map.* (#18471 )
* common : rename speculative.draftless_type -> speculative.type
* ngram-map : fix uninitialized values
* ngram-map : take into account the input can become shorter
* ngram-map : revert len check for now
* arg : change `--spec-draftless` -> `--spec-type`
* spec : add common_speculative_state::accept()
* spec : refactor + add common_speculative_begin()
* spec : fix begin() call with mtmd
* spec : additional refactor + remove common_speculative_params
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com >
2026-01-28 19:42:42 +02:00
60368e1d73
jinja : undefined should be treated as sequence/iterable (return string/array) by filters/tests ( #19147 )
...
* undefined is treated as iterable (string/array) by filters
`tojson` is not a supported `undefined` filter
* add tests
* add sequence and iterable tests
keep it DRY and fix some types
2026-01-28 14:40:29 +01:00
631cbfcc7a
cuda : fix "V is K view" check for non-unified KV cache ( #19145 )
2026-01-28 09:15:27 +02:00
c5c64f72ac
llama : disable Direct IO by default ( #19109 )
...
* llama : disable Direct IO by default
* cont : override mmap if supported
2026-01-28 09:11:13 +02:00
2b4cbd2834
jinja : implement mixed type object keys ( #18955 )
...
* implement mixed type object keys
* add tests
* refactor
* minor fixes
* massive refactor
* add more tests
* forgotten tuples
* fix array/object is_hashable
* correct (albeit broken) jinja responses
verified with transformers
* improved hashing and equality
* refactor hash function
* more exhausive test case
* clean up
* cont
* cont (2)
* missing cstring
---------
Co-authored-by: Xuan Son Nguyen <son@huggingface.co >
2026-01-27 19:50:42 +01:00
f6ece6fd37
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/workflows/check-vendor.yml
# .github/workflows/close-issue.yml
# .github/workflows/editorconfig.yml
# .github/workflows/gguf-publish.yml
# .github/workflows/labeler.yml
# .github/workflows/pre-tokenizer-hashes.yml
# .github/workflows/python-check-requirements.yml
# .github/workflows/python-lint.yml
# .github/workflows/python-type-check.yml
# .github/workflows/server.yml
# .github/workflows/update-ops-docs.yml
# README.md
# docs/build.md
# examples/model-conversion/scripts/utils/perplexity-gen.sh
# examples/model-conversion/scripts/utils/perplexity-run-simple.sh
# examples/model-conversion/scripts/utils/perplexity-run.sh
# examples/model-conversion/scripts/utils/quantize.sh
# examples/model-conversion/scripts/utils/run-embedding-server.sh
# ggml/src/ggml-cpu/ggml-cpu.c
# ggml/src/ggml-hexagon/htp/flash-attn-ops.c
# ggml/src/ggml-opencl/CMakeLists.txt
# ggml/src/ggml-opencl/ggml-opencl.cpp
# ggml/src/ggml-opencl/kernels/cvt.cl
# ggml/src/ggml-opencl/kernels/mul_mv_q6_k_f32.cl
# ggml/src/ggml-sycl/ggml-sycl.cpp
# scripts/compare-llama-bench.py
# tests/test-backend-ops.cpp
# tests/test-gguf.cpp
# tools/cli/README.md
# tools/completion/README.md
# tools/server/README.md
2026-01-27 23:06:13 +08:00
Tarek Dakhran
Piotr Wilkin (ilintar)
Adrien Gallouët
Concedo
Ivan Chikish
iMil
agent-enemy-2
Georgi Gerganov
Daniel Bevenius
thecaptain789
Xuan-Son Nguyen
Sascha Rogmann
Sid Mohan
Marcello Seri
Aldehir Rojas
Sigbjørn Skjæret