cora4 8e2d83cfee Fix per_layer_token_embedding (#2117) ... Co-authored-by: cora4 <you@example.com>		2026-07-12 11:58:09 +03:00
..
baby-llama	…
batched	…
batched-bench	…
batched.swift	…
benchmark	…
convert-llama2c-to-ggml	…
cvector-generator	Split mode graph for dense Gemma4 assistant (#2022)	2026-06-24 18:29:32 +02:00
deprecation-warning	…
embedding	…
eval-callback	eval-callback : sum over the full tensor, not just the printed slice (#2019)	2026-06-24 08:57:19 +02:00
export-lora	…
gbnf-validator	…
gguf	…
gguf-hash	…
gguf-split	…
gritlm	…
imatrix	Fix DFlash oerformance with split mode graph (#1980)	2026-06-17 18:40:02 +02:00
infill	…
jeopardy	…
llama-bench	Remove deprecated Kompute (Vulkan compute) backend (#2097)	2026-07-08 10:01:01 +02:00
llama.android	…
llama.swiftui	…
lookahead	…
lookup	…
main	feat: allow dflash to work with spec auto tune (#2112)	2026-07-12 07:49:03 +03:00
main-cmake-pkg	…
mtmd	mtmd: add MiniMax M3 vision support (#2086)	2026-07-12 07:19:14 +03:00
parallel	…
parser	…
passkey	…
perplexity	on-demand tensor reload (#1989)	2026-06-22 16:36:34 +02:00
quantize	Fix per_layer_token_embedding (#2117)	2026-07-12 11:58:09 +03:00
quantize-stats	Update autofix and presets (#1867)	2026-05-24 07:30:44 +03:00
retrieval	…
rpc	fix(rpc): update ggml_backend_cuda_init to 3-arg signature (#2084)	2026-07-06 09:26:45 +02:00
save-load-state	…
server	feat: allow dflash to work with spec auto tune (#2112)	2026-07-12 07:49:03 +03:00
simple	…
speculative	…
sweep-bench	…
sycl	…
tokenize	…
CMakeLists.txt	…
Miku.sh	…
base-translate.sh	…
chat-13B.bat	…
chat-13B.sh	…
chat-persistent.sh	…
chat-vicuna.sh	…
chat.sh	…
convert_legacy_llama.py	…
json_schema_pydantic_example.py	…
json_schema_to_grammar.py	…
llama.vim	…
llm.vim	…
pydantic_models_to_grammar.py	…
pydantic_models_to_grammar_examples.py	…
reason-act.sh	…
regex_to_grammar.py	…
server-llama2-13B.sh	…
server_embd.py	…
ts-type-to-grammar.sh	…