bench : add --offline (#24511)

• bench : add --offline

Signed-off-by: Adrien Gallouët angt@huggingface.co

• Add default

Signed-off-by: Adrien Gallouët angt@huggingface.co

Signed-off-by: Adrien Gallouët angt@huggingface.co

sycl: support reordered Q4_K/Q5_K/Q6_K MoE MUL_MAT_ID (#24452)

• sycl: support reordered Q4_K and Q5_K MoE MUL_MAT_ID

Extend reordered-weight handling to fused MoE MUL_MAT_ID for Q4_K and Q5_K expert tensors and add Q5_K reordered DMMV coverage. Unsupported 3D reorder cases now fall back instead of aborting.

• sycl: extend MoE reorder to Q6_K mul_mat_id

[SYCL] Support OP EXPM1, support all UT cases of FLOOR, TRUNC, ROUND (#24363)

• support OP EXPM1, support all UT cases of FLOOR, TRUNC, ROUND

• fix conflict

• rebase, support new UT case of repeat, concat

vulkan: add col2im_1d op (#24425)

• vulkan: add GGML_OP_COL2IM_1D, follow-up to the CPU op

• vulkan: col2im_1d bounded gather loop instead of full-K scan with modulo

• vulkan: col2im_1d address review from @jeffbolznv

• vulkan: col2im_1d return nullptr for unsupported types, address review from @0cc4m

chat : fix LFM2 tool-call parsing double-escaping (#24667)

• Add escape test cases

• chat : fix LFM2 tool-call parsing double-escaping

mtmd: fix miscounting n_tokens (#24656)

chat: include full unparsed prompt in debug (#24650)

message on parse error

chat: harden peg-native tool call parsing (#24329)

• chat: harden peg-native tool call parsing

accept an optional leading type: function field in
build_json_tools_flat_keys so openai style tool calls parse on
templates whose serialization opens on the name field.

return a clean error and log the unparsed fragment on a final peg
parse failure instead of throwing the raw parser position and input.

keep the raw arguments string in func_args_not_string when it is not
valid json instead of aborting the prompt render.

• chat: surface peg-native parse failures

a final peg parse failure threw the raw parser position and input. log
the unparsed fragment and raise a clearer error instead, so a model
output that does not match the expected format no longer fails silently
with an empty assistant turn.

minimal change, no behavior change on successful parses.

• chat: handle openai style tool calls in peg-native

• nits

• common: scope OpenAI wrapper grammar trigger via autoparser flag

• chat: gate type:function parsing leniency on the analysis flag

Thread accept_openai_wrapper from the generator to build_json_tools_flat_keys
so the leading "type": "function" field is accepted only when openai_wrapper_trigger is set.

chat: fix an "oldie but goodie" grammar generator bug that surfaced during last changes (#24653)

• chat: fix an "oldie but goodie" grammar generator bug that surfaced during last changes

• update erroneous case in PEG parser test

mtmd : add post-decode callback (#24645)

Assisted-by: pi:llama.cpp/Qwen3.6-27B