Commit Graph
81 Commits
Author SHA1 Message Date
Xuan-Son Nguyen 8d1599fca1 chat: add tts_dict for kokoro G2P template (#32397)
* chat: add tts_dict for kokoro G2P template

* more testing

* value_float_t range check

* no json-in-meta, add llama_model_meta_arr_str/_n
2026-11-17 12:52:50 +01:00
Xuan-Son Nguyen ef6bc6f367 jinja: impl scope-chain key lookup (#32396)
* jinja: impl scope-chain key lookup

* add test for call_statement lambda
2026-11-16 15:48:46 +01:00
Xuan-Son Nguyen e1925b3695 jinja: support json sort_keys=true (#32366) 2026-11-16 12:28:19 +01:00
Pascal a946eb541a server: answer reasoning_effort levels the template rejects with 400 (#32332)
The reasoning effort probe already renders every candidate level, but
it dropped the ones the template raises on, so a request with such a
level (e.g. max on Qwen3.8) reached the template and came back as a
500 on /v1/chat/completions, /v1/responses and /v1/messages.

Keep the raising levels in reasoning_effort_rejected and reject them
in oaicompat_chat_params_parse with an invalid_argument, which the
server answers with a 400 listing the supported levels. Aliases and
levels a template ignores are not rejected, so high on Qwen3.8
still renders as xhigh.

Also trim the output_config.effort test to a single level.
2026-11-16 06:55:56 +01:00
Xuan-Son NguyenandAldehir Rojas b4c0e00a4f jinja: add 4 missing features (#32352)
* jinja: add 4 missing features

* apply suggestion

Co-authored-by: Aldehir Rojas <hello@alde.dev>

* fix error msg

---------

Co-authored-by: Aldehir Rojas <hello@alde.dev>
2026-11-16 00:40:44 +01:00
Xuan Son Nguyen f4d0673917 Revert "jinja: add 4 missing features"
This reverts commit a681a53b60.
2026-11-15 19:35:31 +01:00
Xuan Son Nguyen a681a53b60 jinja: add 4 missing features 2026-11-15 19:33:06 +01:00
HaoJun ZHANGandXuan Son Nguyen 4f2187e73d jinja : reduce template rendering overhead (#32023)
* jinja : reduce value allocation and lookup overhead

Assisted-by: GPT-6 Astra

* jinja : address rendering review feedback

Assisted-by: GPT-6 Astra

* jinja : test multipart strings and simplify lookup

Assisted-by: GPT-6 Astra

* fix "undefined hint"

* fix divisibleby 0

* clean up

---------

Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
2026-11-14 13:34:20 +01:00
Aldehir Rojas cd2db800db jinja : support chained comparisons and argument unpacking (#32072) 2026-11-11 11:53:04 -06:00
MuoDoo 59695669f1 jinja : implement map('filter') (#24033)
* jinja: implement map('filter')

* jinja : validate filter keyword arguments

Assisted-by: Codex
2026-11-02 11:45:40 +01:00
Pascal 1b4554eff1 server: expose the reasoning effort levels of the chat template (#31271)
* server: expose the reasoning effort levels of the chat template

The capability probe renders a user turn for each candidate level
(minimal, low, medium, high, xhigh, max) and for an unknown level. A
level is honored when it renders without raising and differently from
the unknown level, which shows the template fallback. Levels sharing a
render are aliases and the highest one is kept.

The caps serialize to JSON, and chat_template_caps in /props reports
the list as reasoning_effort_levels, from lowest to highest.

* jinja: keep the caps free of the json dependency

The caps keep reporting their flags as a map, and the effort levels
stay a plain member. common_chat_templates_get_caps() builds the JSON
the server reports from both, so jinja depends on json only for the
probe inputs.
2026-10-27 22:39:37 +01:00
Tarek DakhranandAldehir Rojas eb7818c0b8 common : support deferred tools and tool_reference content parts (#31256)
* common : support deferred tools and tool_reference content parts

Assisted-by: Claude Opus 5.5

* common : credit the deferred tools co-author

Co-authored-by: Aldehir Rojas <765227+aldehir@users.noreply.github.com>

Assisted-by: Claude Opus 5.5

* tests : fix the type check of the deferred tools test

Assisted-by: Claude Opus 5.5
2026-10-27 18:39:11 +01:00
48c9f08b7b common, grammar: add recursive depth limit, make it a requirement (#31153)
* common, grammar: add recursive depth limit, make it a requirement

* catch more recursive functions

* common : tidy up peg parser changes

* grammar : reject candidates in a loop, without a depth limit

The depth limit in llama_grammar_reject_candidates_for_stack counted
the code points of a vocab token, so any token of 256 chars or more
was always rejected under a grammar, such as the 512-space token of
GLM-4.7-Flash or the long space tokens of Laguna-S-2.1.

The rejection now walks the code points with its own stack of levels
instead of recursing: there is no limit and no stack risk, whatever
the length of a token from the GGUF, and the masks match master.

* grammar : track rejected candidates as indices into the input

At a given code point a candidate only differs from its input by the
position of its code point pointer, so the levels now carry indices
into the input candidates instead of copies. The first level needs no
special case and the rejects map back to the input directly.

Grammar sampling gets faster than master on GLM-4.7, Laguna, Qwen3.6
and gemma-4 with the json, list and spaces grammars, same masks.

* nit : shorten the comment of llama_grammar_reject_step

* common : add depth_guard for schema walks

* grammar : move GRAMMAR_RECURSIVE_LIMIT into the .cpp

* common : reduce recursion limit for peg parser

* improve

---------

Co-authored-by: Alde Rojas <hello@alde.dev>
Co-authored-by: Pascal <admin@serveurperso.com>
2026-10-25 23:53:08 +01:00
Yuri KhrustalevandXuan Son Nguyen b3fa69955e chat : reject JSON nested more than 128 levels before walking it (#30242)
* chat : reject JSON nested more than 128 levels before walking it

The schema builder, the jinja engine and the decision code walk request
JSON with recursion. A request nested deep enough overflows the stack of
the HTTP thread and llama-server dies (SIGBUS on macOS, SIGSEGV on Linux):
for a tool schema from a few hundred levels on macOS and about 10000 on
Linux.

Check the depth first and answer 400 past 128 levels: the chat inputs in
common_chat_templates_apply (tools, tool-call arguments,
chat_template_kwargs, json_schema), the json_schema of /completion, and the
whole /v1/systemone body. A gemma4 tool result that is too deep stays text.

* fix the root, not the call side

---------

Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
2026-10-25 06:46:35 +01:00
Joseph Patricio d327bf1f07 jinja : fix select and selectattr argument handling (#31059)
* jinja : fix select and selectattr argument handling

* jinja : address review feedback

* jinja : Simplified test attr
2026-10-24 22:54:46 +02:00
Tarek Dakhran 99fb997184 jinja : fix namespace attributes shadowed by dict methods (#30941) 2026-10-21 23:06:56 +02:00
alexey-rsi 9febe63d5a jinja: support hexadecimal string escapes (#30929) 2026-10-21 18:04:36 +02:00
Aldehir Rojas 0ce8cd1141 jinja : implement unique filter (#30819)
* jinja : implement `unique` filter

* cont : inline key_of

* cont : fix alignment
2026-10-19 12:18:24 -05:00
Daniel Han 01fc3aae84 model: add Beam (Reflection) (#30670) 2026-10-17 00:07:55 +02:00
William Tan 08698c81ed jinja : improve context copy constructor performance (#30562)
Assisted-by: Codex
2026-10-15 11:00:57 +02:00
Yuri Khrustalev 82e1e2fd84 jinja : write nan and inf in tojson as json.dumps does (#30483)
tojson wrote nan, inf and -inf for these floats, as values and as dict
keys; json.dumps writes NaN, Infinity and -Infinity. The string and safe
filters of a float keep nan and inf, as Python's str() does, so they no
longer use the tojson function. float_to_json is renamed float_repr, as
it now gives str(); float_json gives the json.dumps text.

Also say in a comment why a last digit 9 is not bumped at a power of 2.
2026-10-15 10:49:40 +02:00
William Tan 2130ca8476 jinja : fix loop body variable scoping (#30533)
Assisted-by: Codex
2026-10-15 09:14:01 +02:00
Yuri Khrustalev 77390baa18 jinja : write floats in tojson as Python does (#30362)
tojson printed floats through a C++ stream (6 significant digits, no
".0"), so 48.858844 became 48.8588 and 1.0 became 1 in tool definitions,
tool-call arguments and other template output. Write the shortest digits
that read back as the same value, as json.dumps does. The string and safe
filters of a float use the same code.
2026-10-14 09:18:38 +03:00
Xuan-Son Nguyen ff026f8c0a chat: replace output string with parts (#30389)
* chat: replace output string with parts

* reserve first
2026-10-14 01:03:56 +02:00
4625240437 model : add K2 Horizon dense and MoVA support (#29535)
* model: K2 Horizon gguf conversion code

* model: loading hparams and tensors in k2-horizon.cpp

* model: K2 Horizon compute graph

* model: K2 Horizon compute graph adjustment and registering tokenizers

* model: K2 Horizon chat template and accomodate safetensors naming

* unicode : add the K2-Horizon pre-tokenizer splitter

The K2-Horizon regex had no arm in unicode_regex_split_custom and fell through to the
general std::regex fallback, which fails two ways.

On MSVC std::regex rejects \p{...}, so no K2-Horizon GGUF loads on Windows at all:
llama-quantize, llama-imatrix and llama-perplexity all abort with
regex_error(error_escape) before a token is produced.

Where the fallback does compile it is still wrong. unicode_regex_split collapses each
codepoint to a single byte naming its Unicode category before matching, and U+200C/U+200D
are category Control, which has no entry in k_ucat_cpt, so both become the 0xD0 fallback
byte. The literal ‌ and ‍ alternatives in K2's regex can then never match and
every ZWNJ or ZWJ ends a letter run.

The splitter is the existing llama3 one with a single rule widened, since K2's regex
differs from llama3's only in that a letter run also takes marks, ZWNJ and ZWJ.

tests/test-unicode.cpp gains a case for this: it fails before the change with
[Amy] [ZWNJ khaham] and passes after with the run intact.

* tests: expand K2 Horizon unicode splitter coverage

* unicode: handle K2 Horizon case folding and empty input

Assisted-by: Codex

* jinja : support sequence indices in selectattr and rejectattr

Assisted-by: Codex

* model : add K2 Horizon dense and MoVA support

Includes the K2 Horizon implementation from ifm-ai/llama.cpp with converter, tensor-parallel and model save/reload fixes.

Assisted-by: Codex

* chat : support K2 Horizon reasoning and tool calls

Assisted-by: Codex

* conversion: remove obsolete K2 Aurora alias

Assisted-by: Codex

* k2-horizon: enforce response schemas and load YaRN betas

Constrain final JSON after reasoning, accept flexible JSON tool envelopes,
enforce XML dialects, and handle repeated or alternate thinking markers.
Load YaRN beta metadata instead of retaining the default values.

Add schema, streaming, continuation, and model reload regressions. Validate
CUDA and CPU builds and 0.9B, 4B, and MoVA conversation/tool round trips.

Assisted-by: Codex

* renaming template fixture

* adressing cisc follows ups

* desloppify the parser / adress aldehir comments

* clean test-chat

* remove fallback : model trained mostly on high anyway

* fix k2 attn_v_exp tn splitting and metal fusion baseline

* k2-horizon : forward expand views before sums

* k2-horizon: copy embds before group norm to fix TP

* disable tesnor parallelism

---------

Co-authored-by: Ryandito Diandaru <ryandito.diandaru@mbzuai.ac.ae>
Co-authored-by: WestWaters <mario.papaleo2013@gmail.com>
Co-authored-by: Natani L. Mayday <71436458+TaskPuppyNatani@users.noreply.github.com>
Co-authored-by: West <100190545+WestWaters@users.noreply.github.com>
Co-authored-by: aaryamonvikram <aaryamonvikram@gmail.com>
Co-authored-by: aaryamonvikram <96529820+aaryamonvikram@users.noreply.github.com>
2026-10-06 18:42:24 +02:00
a u s t i n def4d406ae jinja : skip copying loop scope unless a loop filter needs it (#29776) 2026-10-01 10:10:57 +02:00
Sigbjørn Skjæret ca2e2037b6 jinja : support coerced array attributes (#29574)
* support coerced array attributes

* add tests
2026-09-30 15:33:26 +02:00
Sigbjørn Skjæret 33c923db1b jinja : add support for dict builtin (#29477)
* add support for dict builtin

* add tests
2026-09-27 13:41:50 +02:00
Sigbjørn Skjæret 81bc6b83f8 jinja : implement sameas test (#29448)
* implement sameas test

* add tests
2026-09-26 10:14:58 +02:00
Sigbjørn Skjæret 86a24a182b jinja : fix compile error (#29468) 2026-09-26 09:43:47 +02:00
Sigbjørn Skjæret a1de614ba3 jinja : support noncall test statements with arg (#29443)
* support noncall test statements with arg

* add tests
2026-09-26 08:56:48 +02:00
Si Chen 4e416ee730 jinja : parse unary +/- before variables (#29244)
* jinja : parse unary +/- before variables

Lexer already emits unary_operator for -n / +n, and runtime executes
unary -. Parse them at multiplicative precedence so slices like
items[:-n] and GigaChat indent[:-indent_factor] work.

* jinja : keep filters/tests outside unary operands

Unary +/- must bind only the primary/postfix operand so -n|abs is
(-n)|abs, not -(n|abs). Add unary + and filter/test regression coverage.

Signed-off-by: sinksilk <785976238@qq.com>

---------

Signed-off-by: sinksilk <785976238@qq.com>
2026-09-23 13:29:45 +02:00
Georgi Gerganov 709fe755df jinja : fix dangling reference warning in for_statement (#29279)
Avoid returning references through lambdas that hold a local cast pointer, which triggers -Werror=dangling-reference in some CI compilers. Reuse the precomputed select_expr pointer directly.

Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp
2026-09-22 21:45:33 +02:00
Xuan-Son Nguyen 348f853b7a jinja: use const for statement::execute and ::visit (#29271) 2026-09-22 15:27:59 +02:00
Sigbjørn Skjæret ae9afff8d2 jinja : support dot property integer literals (#28817) 2026-09-12 23:49:53 +03:00
Pascal b31b71f3a0 jinja: treat a null left operand of in as a plain lookup (#28620)
Templates that default an optional variable to none and then test its
membership in a map hit an error, while the same expression is a normal
lookup returning false in Jinja. The undefined counterpart of this case
was already handled just above.
2026-09-09 10:08:27 +03:00
Sigbjørn Skjæret 5202104b59 caps : recheck typed content if template checks for string (#28511) 2026-09-07 09:14:32 +02:00
Xuan-Son Nguyen d9f918d2d0 common: add json.h abstraction (#27511)
* add common/json

* migrate common

* adapt jinja

* migrate server

* big wip

* migrate tests

* wip

* revert some excessive changes

* wip

* wip 2

* revert redundant changes

* fix server crash

* various fixes

* fix ci

* harden a bit

* clean up

* rm json-shim

* add some comments

* rm redundant decl
2026-08-22 16:28:28 +02:00
Xuan-Son Nguyen b94041a98e chat: refactor handling supports_string_content / supports_typed_content (#27130)
* better supports_string_content cap detect

* test: add "skip"

* messages_inp_normalizer
2026-08-16 12:45:33 +02:00
0 9e40df63ba jinja : fix quadratic cost in gather_string_parts (#27034)
* jinja : fix quadratic cost in gather_string_parts

* fix some comments

* remove test
2026-08-14 23:34:40 +02:00
Andy WilliamsandAlde Rojas 7e4c0a9688 chat : pass reasoning_effort to template
* chat: add reasoning_effort to common_chat_templates_inputs

Store OpenAI Chat Completions reasoning_effort and make it
available to jinja templates (with model specific translations
where required).

Assisted-by: llama.cpp:Muse-Glimmer-30B

* server : fixup reading reasoning effort from body

server_chat_convert_responses_to_chatcmpl already handles conversion of
Responses API reasoning.effort to reasoning_effort

* chat : expose reasoning effort

Assisted-by: Claude Opus 5

* chat : add reasoning_effort to generation_params

Assisted-by: Claude Opus 5

* chat : move reasoning_effort next to enable_thinking

Assisted-by: Claude Opus 5

* cont : mirror preserve_reasoning

* cont : pass context through analyze function

---------

Co-authored-by: Alde Rojas <hello@alde.dev>
2026-08-14 13:23:11 -05:00
Thiago Padilha 0ef6e55edb chat : add new template for DeepSeek V4 Flash 0731 (#26398)
* common/chat: update DeepSeek V4 templates

Align the DeepSeek V4 templates with the official encoders while keeping parser behavior out of this change.

- Default drop_thinking for DeepSeek V4 history so prior thinking is omitted unless preserve_reasoning is requested or tools are present.
- Add structured output response-format instructions to the V4 templates and pass the schema into template rendering.
- Add a separate Flash 0731 template for the updated high and max reasoning effort mapping.
- Cover reasoning effort, drop_thinking, structured output prompts, preserved reasoning, continuations, and empty tool arguments in template rendering tests.

Official references:
https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash/blob/main/encoding/encoding_dsv4.py
https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731/blob/main/encoding/encoding_dsv4.py

Assisted-by: Codex

* Fix deepseek v4 0731 template selection

* remove unneeded lower normalization

* Fix DSML parser to consume the tool call separator

* address aldehir requests

* address aldehir comment
2026-08-03 17:59:11 -05:00
Piotr Wilkin (ilintar) e8e6c7af24 minor: fix reasoning preserve var for DS4 [no ci] (#25999) 2026-07-22 14:32:54 +02:00
Piotr Wilkin (ilintar) f534da26e4 Fix DeepSeek4 crafted template (#25414)
* chat: fix DS4 template to explicitly follow reference behavior

* Support DeepSeekv4 flag (`drop_reasoning`).

* fix: hook DS3.2 parser for DS4 as well

* fix: add tool result reordering

* fix: post-merge
2026-07-22 12:54:40 +02:00
2969d6d15d model: add Hy3 (hy_v3) support with MTP speculative decoding (#25395)
* model: add Hy3 (hy_v3) architecture support

Adds Tencent Hunyuan 3 (HF architecture HYV3ForCausalLM, GGUF arch
hy_v3): a MoE decoder stack with per-head Q/K RMSNorm, a sigmoid
router with expert selection bias, an always-active ungated shared
expert, and leading dense block(s) (first_k_dense_replace).

The base implementation is ported from charlie12345's fork
(https://github.com/charlie12345/ROCmFPX, src/models/hyv3.cpp),
adapted to current mainline APIs (hparams.n_layer(), build_qkv,
build_moe_ffn with fused gate_up + scale tensors, output_s).

Note: blk.N.exp_probs_b is stored without a .bias suffix for
compatibility with existing hy_v3 GGUFs produced by that fork.

Co-Authored-By: charlie12345 <charlie12345@users.noreply.github.com>
Co-authored-by: Piotr Wilkin <ilintar@gmail.com>
Assisted-by: Claude Fable 5
2026-07-14 00:31:04 +02:00
Xuan-Son Nguyen b3fed31b99 jinja, chat: add --reasoning-preserve flag (#25105)
* jinja, chat: add --reasoning-preserve flag

* correct help message
2026-06-28 23:33:51 +02:00
c818263f2a chat : implement minicpm5 parser (#24889)
* Add minicpm5 tool call parser

* Refactor MiniCPM5 PEG parser per review feedback

* Fix jinja min/max API to match Jinja2

* modify by review

* MiniCPM5: use autoparser for XML tool calls and fix grammar preserved-token triggers

* MiniCPM5: fix streaming tool-arg placeholder and remove alt XML markers

* skip min/max attribute tests in -py mode

* test-jinja: use real expected output for min/max attribute tests

* MiniCPM5: revert shared mapper and history fallbacks per review

Drop streaming tool-arg placeholder workarounds from the generic PEG
mapper and restore strict tool-call argument JSON parsing so MiniCPM5
support stays limited to autoparser/diff-analyzer changes.

* chat : refactor minicpm5 back to dedicated parser

* cont : simplify grammar

* cont : refactor

* cont : fixes

* cont : rename template to openbmb-MiniCPM5-1B.jinja

* cont : add message delimiters

* cont : fix tests

---------

Co-authored-by: zhangtao <zhangtao2@modelbest.cn>
Co-authored-by: 张涛 <>
2026-06-28 16:53:32 +02:00
Xuan-Son NguyenandSigbjørn Skjæret f68a788b0b jinja: add --dump-prog for debugging (#25086)
* jinja: add --dump-prog for debugging

* Update common/jinja/runtime.cpp

Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com>

---------

Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com>
2026-06-28 15:50:31 +02:00
Sigbjørn Skjæret bf533823cd jinja : implement call statement (#24847)
* implement call statement

* undo unintended change

* de-lambda

* simplify

* move caller context inside function handler
2026-06-21 14:04:52 +02:00
Sigbjørn Skjæret acd79d603c jinja : add count/d/e filter aliases (#24606) 2026-06-14 15:07:31 +02:00