Johannes Gäßler dd373dd3bf llama: fix error on bad grammar (#12628)		2025-03-28 18:08:52 +01:00
..
cmake
minja	sync: minja - support QwQ-32B (#12235)	2025-03-07 09:33:37 +00:00
arg.cpp	server : Support listening on a unix socket (#12613)	2025-03-27 23:41:04 +01:00
arg.h
base64.hpp
build-info.cpp.in
chat.cpp	server: extract <think> tags from qwq outputs (#12297)	2025-03-10 10:59:03 +00:00
chat.h	server: extract <think> tags from qwq outputs (#12297)	2025-03-10 10:59:03 +00:00
CMakeLists.txt	upgrade to llguidance 0.7.10 (#12576)	2025-03-26 11:06:09 -07:00
common.cpp	Load all MoE experts during warmup (#11571)	2025-03-14 13:47:05 +01:00
common.h	common : refactor '-o' option (#12278)	2025-03-10 13:34:13 +02:00
console.cpp
console.h
json-schema-to-grammar.cpp	tool-call: fix Qwen 2.5 Coder support, add micro benchmarks, support trigger patterns for lazy grammars (#12034)	2025-03-05 13:05:13 +00:00
json-schema-to-grammar.h	tool-call: fix Qwen 2.5 Coder support, add micro benchmarks, support trigger patterns for lazy grammars (#12034)	2025-03-05 13:05:13 +00:00
json.hpp
llguidance.cpp	upgrade to llguidance 0.7.10 (#12576)	2025-03-26 11:06:09 -07:00
log.cpp
log.h
ngram-cache.cpp	ggml : portability fixes for VS 2017 (#12150)	2025-03-04 18:53:26 +02:00
ngram-cache.h
sampling.cpp	llama: fix error on bad grammar (#12628)	2025-03-28 18:08:52 +01:00
sampling.h
speculative.cpp	llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)	2025-03-13 12:35:44 +02:00
speculative.h
stb_image.h