 0cc4m
|
ee1628bdfe
Basic Vulkan Multi-GPU implementation (#5321)
|
1 rok temu |
 l3utterfly
|
e6f8177532
common : add dynamic temperature parameters to main example cli (#5295)
|
1 rok temu |
 Michael Klimenko
|
52bb63c708
refactor : switch to emplace_back to avoid extra object (#5291)
|
1 rok temu |
 Georgi Gerganov
|
5cb04dbc16
llama : remove LLAMA_MAX_DEVICES and LLAMA_SUPPORTS_GPU_OFFLOAD (#5240)
|
1 rok temu |
|
0cc4m
|
f8e9140cb4
Vulkan Fixes (#5223)
|
1 rok temu |
 Jared Van Bortel
|
e8dc55d006
kompute : llama-bench support and ggml_cpu_has_kompute() (#5226)
|
1 rok temu |
 Abhilash Majumder
|
0f648573dd
ggml : add unified SYCL backend for Intel GPUs (#2690)
|
2 lat temu |
|
Georgi Gerganov
|
89758723c7
minor : clean-up some warnings and style (#5094)
|
2 lat temu |
 Kawrakow
|
6f9939d119
KL-divergence (#5076)
|
2 lat temu |
|
Kawrakow
|
7dcbe39d36
Add ability to evauate multiple choice tasks (#5047)
|
2 lat temu |
|
Kawrakow
|
682986a08e
Add Winogrande evaluation (#5015)
|
2 lat temu |
 stduhpf
|
e0324285a5
speculative : threading options (#4959)
|
2 lat temu |
 Yann Follet
|
722d33f34e
main : add parameter --no-display-prompt (#4541)
|
2 lat temu |
 slaren
|
e7e4df031b
llama : ggml-backend integration (#4766)
|
2 lat temu |
 howlger
|
4315a94366
common : streamline the formatting of help (#4890)
|
2 lat temu |
|
Georgi Gerganov
|
f445c0e68c
llama : fix llm_build_k_shift to use correct n_rot (#4889)
|
2 lat temu |
|
Georgi Gerganov
|
7edefbd79c
main : better name for variable n_print (#4874)
|
2 lat temu |
|
Georgi Gerganov
|
3ca63b4538
main : disable token count by default (#4874)
|
2 lat temu |
 pudepiedj
|
43f76bf1c3
main : print total token count and tokens consumed so far (#4874)
|
2 lat temu |
|
howlger
|
1fc2f265ff
common : fix the short form of `--grp-attn-w`, not `-gat` (#4825)
|
2 lat temu |
|
Georgi Gerganov
|
52531fdff8
main : add self-extend support (#4815)
|
2 lat temu |
 automaticcat
|
24a447e20a
ggml : add ggml_cpu_has_avx_vnni() (#4589)
|
2 lat temu |
|
Jared Van Bortel
|
8fe03ffdda
common : remove incorrect --model-draft default (#4568)
|
2 lat temu |
 Siwen Yu
|
9fb13f9584
common : add `--version` option to show build info in CLI (#4433)
|
2 lat temu |
|
Georgi Gerganov
|
bcc0eb4591
llama : per-layer KV cache + quantum K cache (#4309)
|
2 lat temu |
 Kerfuffle
|
5aa365d88f
llama : allow overriding GGUF metadata when loading model (#4092)
|
2 lat temu |
 MaggotHATE
|
52c8bc3cf3
sampling : custom samplers order (#4285)
|
2 lat temu |
|
Georgi Gerganov
|
6b0a7420d0
llama : KV cache view API + better KV cache management (#4170)
|
2 lat temu |
 Seb C
|
881800d1f0
main : Add ChatML functionality to main example (#4046)
|
2 lat temu |
 kchro3
|
262005ad9d
common : comma should be semicolon (#4137)
|
2 lat temu |
