| .. |
|
batched
|
6ab8eacddf
examples : add -kvu to batched usage example [no ci] (#17469)
|
il y a 1 mois |
|
batched.swift
|
29f538ac63
examples : remove references to `make` in examples [no ci] (#15457)
|
il y a 5 mois |
|
convert-llama2c-to-ggml
|
a81283820a
gguf: gguf_writer refactor (#15691)
|
il y a 4 mois |
|
deprecation-warning
|
f112d198cd
Update deprecation-warning.cpp (#10619)
|
il y a 1 an |
|
diffusion
|
4902eebe33
models : Added support for RND1 Diffusion Language Model (#17433)
|
il y a 1 mois |
|
embedding
|
e072b2052e
ggml : add GGML_SCHED_NO_REALLOC option to disable reallocations in ggml_backend_sched (#17276)
|
il y a 1 mois |
|
eval-callback
|
196f5083ef
common : more accurate sampling timing (#17382)
|
il y a 1 mois |
|
gen-docs
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
il y a 1 an |
|
gguf
|
5886f4f545
examples(gguf): GGUF example outputs (#17025)
|
il y a 2 mois |
|
gguf-hash
|
53ff6b9b9f
GGUF: C++ refactor, backend support, misc fixes (#11030)
|
il y a 1 an |
|
idle
|
c41bde6fbd
metal : add residency sets keep-alive heartbeat (#17766)
|
il y a 1 mois |
|
llama.android
|
745aa5319b
llama : deprecate llama_kv_self_ API (#14030)
|
il y a 7 mois |
|
llama.swiftui
|
745aa5319b
llama : deprecate llama_kv_self_ API (#14030)
|
il y a 7 mois |
|
lookahead
|
2f37014073
lookahead : add sample command to readme (#15447)
|
il y a 5 mois |
|
lookup
|
745aa5319b
llama : deprecate llama_kv_self_ API (#14030)
|
il y a 7 mois |
|
model-conversion
|
2fa51c19b0
model-conversion : add token ids to prompt token output [no ci] (#17863)
|
il y a 1 mois |
|
parallel
|
2adf8d83ac
parallel : add option for different RNG seeds (#14757)
|
il y a 6 mois |
|
passkey
|
29f538ac63
examples : remove references to `make` in examples [no ci] (#15457)
|
il y a 5 mois |
|
retrieval
|
29f538ac63
examples : remove references to `make` in examples [no ci] (#15457)
|
il y a 5 mois |
|
save-load-state
|
8ce774a102
metal : fix build(#17799)
|
il y a 1 mois |
|
simple
|
1cbd80f8cf
examples : support encoder-decoder models in the simple example (#16002)
|
il y a 4 mois |
|
simple-chat
|
d7f5f4e578
simple-chat : fix context-exceeded condition (#14494)
|
il y a 6 mois |
|
simple-cmake-pkg
|
817d743cc1
examples : add missing code block end marker [no ci] (#17756)
|
il y a 1 mois |
|
speculative
|
e92d53b29e
sampling : optimize samplers by reusing bucket sort (#15665)
|
il y a 4 mois |
|
speculative-simple
|
d8914fc47e
common : add --override-tensor-draft, --cpu-moe-draft and --n-cpu-moe-draft parameters (#15191)
|
il y a 5 mois |
|
sycl
|
7d2add51d8
sycl : support to malloc memory on device more than 4GB, update the doc and script (#17566)
|
il y a 1 mois |
|
training
|
5cdb27e091
finetune: SGD optimizer, more CLI args (#13873)
|
il y a 5 mois |
|
CMakeLists.txt
|
c41bde6fbd
metal : add residency sets keep-alive heartbeat (#17766)
|
il y a 1 mois |
|
convert_legacy_llama.py
|
a0ec17b32e
metadata: Detailed Dataset Authorship Metadata (#8875)
|
il y a 1 an |
|
json_schema_pydantic_example.py
|
3fd62a6b1c
py : type-check all Python scripts with Pyright (#8341)
|
il y a 1 an |
|
json_schema_to_grammar.py
|
0874693b44
common : fix json schema with '\' in literals (#17307)
|
il y a 1 mois |
|
llama.vim
|
9ebebef62f
llama : remove KV cache defragmentation logic (#15473)
|
il y a 4 mois |
|
pydantic_models_to_grammar.py
|
090fca7a07
pydantic : replace uses of __annotations__ with get_type_hints (#8474)
|
il y a 1 an |
|
pydantic_models_to_grammar_examples.py
|
1d36b3670b
llama : move end-user examples to tools directory (#13249)
|
il y a 8 mois |
|
reason-act.sh
|
e9b6350e61
scripts : make the shell scripts cross-platform (#14341)
|
il y a 6 mois |
|
regex_to_grammar.py
|
e235b267a2
py : switch to snake_case (#8305)
|
il y a 1 an |
|
server-llama2-13B.sh
|
e9b6350e61
scripts : make the shell scripts cross-platform (#14341)
|
il y a 6 mois |
|
server_embd.py
|
a19b5cef16
llama : fix FA when KV cache is not used (i.e. embeddings) (#12825)
|
il y a 9 mois |
|
ts-type-to-grammar.sh
|
e9b6350e61
scripts : make the shell scripts cross-platform (#14341)
|
il y a 6 mois |
Daniel Bevenius
2fa51c19b0
model-conversion : add token ids to prompt token output [no ci] (#17863)