 takasurazeem
|
6f5d924637
common : Update the docs on -t --threads (#16236)
|
3 mesiacov pred |
 Georgi Gerganov
|
4b2dae383d
common : update presets (#16504)
|
3 mesiacov pred |
|
Georgi Gerganov
|
d00cbea63c
server : host-memory prompt caching (#16391)
|
3 mesiacov pred |
 Pascal
|
12bbc3fa50
refactor: centralize CoT parsing in backend for streaming mode (#16394)
|
3 mesiacov pred |
|
Georgi Gerganov
|
ef4c5b87ea
presets : fix pooling param for embedding models (#16455)
|
3 mesiacov pred |
 Gadflyii
|
3df2244df4
llama : add --no-host to disable host buffers (#16310)
|
3 mesiacov pred |
 Radoslav Gerganov
|
898acba681
rpc : add support for multiple devices (#16276)
|
3 mesiacov pred |
 ddh0
|
f6dcda3900
server : context checkpointing for hybrid and recurrent models (#16382)
|
3 mesiacov pred |
 Adrien Gallouët
|
4201deae9c
common: introduce http.h for httplib-based client (#16373)
|
3 mesiacov pred |
 Adrien Gallouët
|
bf6f3b3a19
common : disable progress bar without a tty (#16352)
|
3 mesiacov pred |
|
Adrien Gallouët
|
364a7a6d4a
common : remove common_has_curl() (#16351)
|
3 mesiacov pred |
|
Adrien Gallouët
|
3c62aed89f
common : simplify etag tracking by removing json (#16342)
|
3 mesiacov pred |
|
Adrien Gallouët
|
b995a10760
common : use cpp-httplib as a cURL alternative for downloads (#16185)
|
3 mesiacov pred |
|
Adrien Gallouët
|
37a23c17bd
common : enable `--offline` mode without curl support (#16137)
|
3 mesiacov pred |
 Haiyue Wang
|
d05affbab7
common : remove unused local variables (#16140)
|
3 mesiacov pred |
 Eric Curtin
|
4ca088b036
Add resumable downloads for llama-server model loading (#15963)
|
4 mesiacov pred |
 jacekpoplawski
|
8ff206097c
llama-bench: add --n-cpu-moe support (#15952)
|
4 mesiacov pred |
 Aman Gupta
|
6d758839ff
Add LLaDA-7b-MoE diffusion model (#16003)
|
4 mesiacov pred |
 Diego Devesa
|
50f4281a6f
llama : allow using iGPUs with --device (#15951)
|
4 mesiacov pred |
|
Eric Curtin
|
4bf5549269
Add docker protocol support for llama-server model loading (#15790)
|
4 mesiacov pred |
 Eric Curtin
|
408ff524b4
Implement --log-colors with always/never/auto (#15792)
|
4 mesiacov pred |
 Eric Curtin
|
badb80cadb
Document the new max GPU layers default in help (#15771)
|
4 mesiacov pred |
 Johannes Gäßler
|
c466abe158
llama: -fa 1/0/-1 aliases for -fa on/off/auto (#15746)
|
4 mesiacov pred |
|
Georgi Gerganov
|
0d161f021a
server : enable /slots by default and make it secure (#15630)
|
4 mesiacov pred |
|
Johannes Gäßler
|
e81b8e4b7f
llama: use FA + max. GPU layers by default (#15434)
|
4 mesiacov pred |
 Sigbjørn Skjæret
|
84ab83cc0b
model : jina-embeddings-v3 support (#13693)
|
4 mesiacov pred |
|
Georgi Gerganov
|
da54f9f1a2
presets : add qwen3-30B-a3b FIM (#15616)
|
4 mesiacov pred |
 Daniel Bevenius
|
fcca2182a1
common : add -m to bash completion for --model [no ci] (#15591)
|
4 mesiacov pred |
|
Georgi Gerganov
|
9ebebef62f
llama : remove KV cache defragmentation logic (#15473)
|
4 mesiacov pred |
|
Diego Devesa
|
54a241f505
sched : fix possible use of wrong ids tensor when offloading moe prompt processing (#15488)
|
4 mesiacov pred |
