 Georgi Gerganov
|
a4090d1174
llama : remove llama_kv_cache_view API + remove deprecated (#13653)
|
8 maanden geleden |
|
Georgi Gerganov
|
e298d2fbd0
kv-cache : add SWA support (#13194)
|
8 maanden geleden |
 psocolovsky
|
1dfbf2cf3a
common : add load_progress_callback (#13617)
|
8 maanden geleden |
 Olivier Chafik
|
3198405e98
`common`: add partial regex support (#12808)
|
8 maanden geleden |
 Johannes Gäßler
|
10d2af0eaa
llama/ggml: add LLM training support (#10544)
|
8 maanden geleden |
 David Huang
|
7f323a589f
Add `--no-op-offload` to improve `-ot` pp perf in MoE models like llama4 400B (#13386)
|
8 maanden geleden |
|
Georgi Gerganov
|
51fb96b1ff
context : remove logits_all flag (#13284)
|
8 maanden geleden |
 Prajwal B Mehendarkar
|
bc091a4dc5
common : Define cache directory on AIX (#12915)
|
9 maanden geleden |
 yuri@FreeBSD
|
68b08f36d0
common : Define cache directory on FreeBSD (#12892)
|
9 maanden geleden |
 tastelikefeet
|
b2034c2b55
contrib: support modelscope community (#12664)
|
9 maanden geleden |
 Diego Devesa
|
e0e912f49b
llama : add option to override model tensor buffers (#11397)
|
9 maanden geleden |
 Xuan-Son Nguyen
|
42eb248f46
common : remove json.hpp from common.cpp (#12697)
|
9 maanden geleden |
|
Xuan-Son Nguyen
|
267c1399f1
common : refactor downloading system, handle mmproj with -hf option (#12694)
|
9 maanden geleden |
 fairydreaming
|
8fcb563613
Load all MoE experts during warmup (#11571)
|
10 maanden geleden |
|
Georgi Gerganov
|
e0dbec0bc6
llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)
|
10 maanden geleden |
|
Olivier Chafik
|
669912d9a5
`tool-call`: fix Qwen 2.5 Coder support, add micro benchmarks, support trigger patterns for lazy grammars (#12034)
|
10 maanden geleden |
|
Olivier Chafik
|
63e489c025
tool-call: refactor common chat / tool-call api (+ tests / fixes) (#11900)
|
11 maanden geleden |
|
Olivier Chafik
|
9f4cc8f8d3
`sync`: minja (#11641)
|
11 maanden geleden |
|
Olivier Chafik
|
cde3833239
`tool-call`: allow `--chat-template chatml` w/ `--jinja`, default to chatml upon parsing issue, avoid double bos (#11616)
|
11 maanden geleden |
|
Olivier Chafik
|
8b576b6c55
Tool call support (generic + native for Llama, Functionary, Hermes, Mistral, Firefunction, DeepSeek) w/ lazy grammars (#9639)
|
11 maanden geleden |
|
Olivier Chafik
|
a94f3b2727
`common`: utils to split / join / repeat strings (from json converter) (#11342)
|
1 jaar geleden |
|
Olivier Chafik
|
6171c9d258
Add Jinja template support (#11016)
|
1 jaar geleden |
 Radoslav Gerganov
|
667d72846c
rpc : early register backend devices (#11262)
|
1 jaar geleden |
 Xuan Son Nguyen
|
00b4c3da62
common : support tag-based --hf-repo like on ollama (#11195)
|
1 jaar geleden |
|
Xuan Son Nguyen
|
9a483999a6
llama : fix chat template gguf key (#11201)
|
1 jaar geleden |
|
Georgi Gerganov
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
1 jaar geleden |
|
Johannes Gäßler
|
53ff6b9b9f
GGUF: C++ refactor, backend support, misc fixes (#11030)
|
1 jaar geleden |
|
Georgi Gerganov
|
47182dd03f
llama : update llama_model API names (#11063)
|
1 jaar geleden |
|
Georgi Gerganov
|
727368c60f
llama : use LLAMA_TOKEN_NULL (#11062)
|
1 jaar geleden |
 Molly Sophia
|
4b0c638b9a
common : disable KV cache shifting automatically for unsupported models (#11053)
|
1 jaar geleden |
