 Georgi Gerganov
|
22229314fc
llama : clarify deprecation message (#13794)
|
hai 8 meses |
|
Georgi Gerganov
|
de2ef53a4b
kv-cache : rework kv_cell (#13706)
|
hai 8 meses |
|
Georgi Gerganov
|
797f2ac062
kv-cache : simplify the interface (#13660)
|
hai 8 meses |
|
Georgi Gerganov
|
a4090d1174
llama : remove llama_kv_cache_view API + remove deprecated (#13653)
|
hai 8 meses |
|
Georgi Gerganov
|
e298d2fbd0
kv-cache : add SWA support (#13194)
|
hai 8 meses |
 Diego Devesa
|
cf0a43bb64
llama-bench : add defrag-thold, check for invalid ranges (#13487)
|
hai 8 meses |
 Johannes Gäßler
|
10d2af0eaa
llama/ggml: add LLM training support (#10544)
|
hai 8 meses |
 David Huang
|
7f323a589f
Add `--no-op-offload` to improve `-ot` pp perf in MoE models like llama4 400B (#13386)
|
hai 8 meses |
 Sigbjørn Skjæret
|
d2a4ef05c6
vocab : add ByteDance-Seed/Seed-Coder (#13423)
|
hai 8 meses |
|
Georgi Gerganov
|
6562e5a4d6
context : allow cache-less context for embeddings (#13108)
|
hai 8 meses |
|
Georgi Gerganov
|
51fb96b1ff
context : remove logits_all flag (#13284)
|
hai 8 meses |
|
Georgi Gerganov
|
d9d398f84f
sampling : when top-k <= 0 -> noop (#13173)
|
hai 8 meses |
 Xuan-Son Nguyen
|
ecda2ec4b3
mtmd : Support Pixtral 12B (#13065)
|
hai 9 meses |
 Ed Addario
|
71e90e8813
quantize: Handle user-defined quantization levels for additional tensors (#12511)
|
hai 9 meses |
|
Xuan-Son Nguyen
|
1466621e73
llama : Support llama 4 text-only (#12791)
|
hai 9 meses |
|
Diego Devesa
|
e0e912f49b
llama : add option to override model tensor buffers (#11397)
|
hai 9 meses |
|
Sigbjørn Skjæret
|
2c3f8b850a
llama : support BailingMoE (Ling) (#12634)
|
hai 9 meses |
 Juyoung Suk
|
b3de7cac73
llama : add Trillion 7B model support (#12556)
|
hai 9 meses |
|
Johannes Gäßler
|
dd373dd3bf
llama: fix error on bad grammar (#12628)
|
hai 10 meses |
 compilade
|
00d53800e0
llama-vocab : add SuperBPE pre-tokenizer (#12532)
|
hai 10 meses |
 fairydreaming
|
8fcb563613
Load all MoE experts during warmup (#11571)
|
hai 10 meses |
|
Georgi Gerganov
|
e0dbec0bc6
llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)
|
hai 10 meses |
 Olivier Chafik
|
669912d9a5
`tool-call`: fix Qwen 2.5 Coder support, add micro benchmarks, support trigger patterns for lazy grammars (#12034)
|
hai 10 meses |
 Xuan-Son Nguyen
|
c43a3e7996
llama : add Phi-4-mini support (supersede #12099) (#12108)
|
hai 10 meses |
 Vitali Lovich
|
3e9a2860e9
llama : expose llama_model_n_head_kv in the API (#11997)
|
hai 11 meses |
|
Georgi Gerganov
|
68ff663a04
repo : update links to new url (#11886)
|
hai 11 meses |
 Vinesh Janarthanan
|
27e8a23300
sampling: add Top-nσ sampler (#11223)
|
hai 11 meses |
 Christian Fillion
|
7ee953a64a
llama : add llama_sampler_init for safe usage of llama_sampler_free (#11727)
|
hai 11 meses |
|
Olivier Chafik
|
8b576b6c55
Tool call support (generic + native for Llama, Functionary, Hermes, Mistral, Firefunction, DeepSeek) w/ lazy grammars (#9639)
|
hai 11 meses |
|
Olivier Chafik
|
6171c9d258
Add Jinja template support (#11016)
|
hai 1 ano |
