 Pedro Cuenca
|
e097633f63
convert-hf : fix exception in sentencepiece with added tokens (#6320)
|
1 year ago |
 Kawrakow
|
d25b1c31b0
quantize : be able to override metadata by key (#6321)
|
1 year ago |
 Minsoo Cheong
|
deb7240100
embedding : adjust `n_ubatch` value (#6296)
|
1 year ago |
 Jan Boon
|
3d032ece8e
server : add `n_discard` parameter (#6300)
|
1 year ago |
 Joseph Stahl
|
e190f1fca6
nix: make `xcrun` visible in Nix sandbox for precompiling Metal shaders (#6118)
|
1 year ago |
 slaren
|
280345968d
cuda : rename build flag to LLAMA_CUDA (#6299)
|
1 year ago |
 Christian Kögler
|
b06c16ef9f
nix: fix blas support (#6281)
|
1 year ago |
|
Kawrakow
|
1f2fd4e727
tests : include IQ2_XXS and IQ2_XS in test-quantize-fns (#6303)
|
1 year ago |
 Georgi Gerganov
|
43139cc528
flake.lock: Update (#6266)
|
1 year ago |
|
slaren
|
2f34b865b6
cuda : fix LLAMA_CUDA_F16 build (#6298)
|
1 year ago |
|
slaren
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 year ago |
 Xuan Son Nguyen
|
ad3a0505e3
Server: clean up OAI params parsing function (#6284)
|
1 year ago |
 Neo Zhang Jianyu
|
95ad616cdd
[SYCL] fix SYCL backend build on windows is break by LOG() error (#6290)
|
1 year ago |
|
Minsoo Cheong
|
64e7b47c69
examples : add "retrieval" (#6193)
|
1 year ago |
 Justine Tunney
|
7733f0c760
ggml : support AVX512VNNI (#6280)
|
1 year ago |
 Rick G
|
a32b77c4b2
Fix heap corruption from wmode out-of-bound writes on windows (#6272)
|
1 year ago |
|
Georgi Gerganov
|
a0e584defd
imatrix : fix wname for mul_mat_id ops (#6271)
|
1 year ago |
 Johannes Gäßler
|
7aed0ffe68
Fixed lookup compilation issues on Windows (#6273)
|
1 year ago |
 Pierrick Hymbert
|
ea279d5609
ci : close inactive issue, increase operations per run (#6270)
|
1 year ago |
|
Minsoo Cheong
|
586e7bc561
sampling : deduplicated code for probability distribution access (#6240)
|
1 year ago |
 Meng, Hengyu
|
ddf6568510
[SYCL] offload op (#6217)
|
1 year ago |
|
Neo Zhang Jianyu
|
d03224ac98
Support build win release for SYCL (#6241)
|
1 year ago |
 Jared Van Bortel
|
94d1b3b411
use _wfopen instead of fopen on Windows (#6248)
|
1 year ago |
|
Georgi Gerganov
|
95562175f8
gitignore : gguf-split
|
1 year ago |
|
Pierrick Hymbert
|
f482bb2e49
common: llama_load_model_from_url split support (#6192)
|
1 year ago |
|
Pierrick Hymbert
|
1997577d5e
server: docs: `--threads` and `--threads`, `--ubatch-size`, `--log-disable` (#6254)
|
1 year ago |
 Julius Arkenberg
|
476b0251b2
llama : add grok-1 support (#6204)
|
1 year ago |
|
Pierrick Hymbert
|
21cad01b6e
split: add gguf-split in the make build target (#6262)
|
1 year ago |
|
Pierrick Hymbert
|
1b26aebe4d
server: flush stdout after logging in both text and json layout (#6253)
|
1 year ago |
|
Johannes Gäßler
|
50ccaf5eac
lookup: complement data from context with general text statistics (#5479)
|
1 year ago |
