 Georgi Gerganov
|
8a203f9fa1
llama : fix compile warnings in llama_set_state_data()
|
2 yıl önce |
|
Georgi Gerganov
|
4fd3e29297
ggml : fix scalar implementation of Q4_1 dot
|
2 yıl önce |
|
Georgi Gerganov
|
2d5db48371
ggml : use F16 instead of F32 in Q4_0, Q4_1, Q8_0 (#1508)
|
2 yıl önce |
|
Georgi Gerganov
|
6986c7835a
tests : add missing header
|
2 yıl önce |
 Evan Jones
|
943e6081cc
examples : add persistent chat (#1495)
|
2 yıl önce |
 Jason McCartney
|
7694b52b9a
main : make reverse prompt option act as a stop token in non-interactive mode (#1032)
|
2 yıl önce |
 David Kennedy
|
79e3efb0e9
readme : adds WizardLM to the list of supported models (#1485)
|
2 yıl önce |
|
Georgi Gerganov
|
4b7e245adf
minor : fix compile warnings
|
2 yıl önce |
 Erik Scholz
|
5ea4339273
make kv_f16 the default for api users (#1517)
|
2 yıl önce |
 DannyDaemonic
|
ee9654138a
Fixes #1511 lambda issue for w64devkit (mingw) (#1513)
|
2 yıl önce |
 Stephan Walter
|
dc271c52ed
Remove unused n_parts parameter (#1509)
|
2 yıl önce |
 rankaiyx
|
c238b5873a
benchmark-matmul: Print the average of the test results (#1490)
|
2 yıl önce |
 Tom Jobbins
|
2b2646931b
convert.py: Support models which are stored in a single pytorch_model.bin (#1469)
|
2 yıl önce |
 Ilya Kurdyukov
|
42627421ec
~7% faster Q5_1 AVX2 code (#1477)
|
2 yıl önce |
 András Salamon
|
9560655409
define default model path once, sync path with readme (#1366)
|
2 yıl önce |
 sandyiscool
|
2a5ee023ad
Add alternate include path for openblas (#1476)
|
2 yıl önce |
 zrm
|
63d20469b8
fix get_num_physical_cores() (#1436)
|
2 yıl önce |
 slaren
|
b5c9295eef
benchmark-matmul: fix clang-tidy issues, report results in GFLOPS (#1458)
|
2 yıl önce |
 Johannes Gäßler
|
eb363627fd
cuda : deduplicated dequantization code (#1453)
|
2 yıl önce |
 xaedes
|
79b2d5b69d
ggml : alternative fix for race condition bug in non-inplace ggml_compute_forward_diag_mask_f32 (#1454)
|
2 yıl önce |
|
Georgi Gerganov
|
13c351ad72
ggml : various fixes (#1450)
|
2 yıl önce |
 katsu560
|
60f8c361ca
ggml : add AVX support based on AVX2 code (#1430)
|
2 yıl önce |
|
Georgi Gerganov
|
601a033475
ggml : add GGML_QNT_VERSION to track quantization format changes
|
2 yıl önce |
|
Georgi Gerganov
|
08737ef720
cuda : fix convert function (#1412)
|
2 yıl önce |
|
Georgi Gerganov
|
bda4d7c215
make : fix PERF build with cuBLAS
|
2 yıl önce |
|
Georgi Gerganov
|
5a5aeb1e91
llama : fix unused warning
|
2 yıl önce |
|
Georgi Gerganov
|
66841fdb0e
ggml : multi-thread mul and diag_mask ops (#1428)
|
2 yıl önce |
|
Johannes Gäßler
|
905d87b70a
ggml : GPU-accelerated token generation (#1412)
|
2 yıl önce |
|
xaedes
|
f954edda93
ggml : implement backward pass for llama + small training-llama-from-scratch example (#1360)
|
2 yıl önce |
|
Georgi Gerganov
|
f048af0230
ggml : sync alibi fix from ggml repo
|
2 yıl önce |
