 R0CKSTAR
|
bb115d2bf7
musa: override warp_size of musa device to 32 (#12445)
|
hai 10 meses |
 Xuan-Son Nguyen
|
29fff308c7
llama : support converting Mistral Small text-only (#12450)
|
hai 10 meses |
 Georgi Gerganov
|
c6af2161b2
speculative : fix seg fault in certain cases (#12454)
|
hai 10 meses |
|
Xuan-Son Nguyen
|
99aa304fb9
llama : add support for EXAONE tied word embeddings (#12451)
|
hai 10 meses |
|
Georgi Gerganov
|
8551c44d84
context : always use non-causal attention for encoder graphs (#12447)
|
hai 10 meses |
 Łukasz Ślusarczyk
|
35cae5ba05
SYCL: using graphs is configurable by environment variable and compile option (#12371)
|
hai 10 meses |
|
Georgi Gerganov
|
810e0af3f5
server : fix warmup draft cache type (#12446)
|
hai 10 meses |
 Prajwal B Mehendarkar
|
eba92d64c3
cmake : fix PowerPC build (#12241)
|
hai 10 meses |
 fj-y-saito
|
d9a14523bb
ggml : add SVE support for q6_K_q8_K (#12361)
|
hai 10 meses |
 0cc4m
|
fd123cfead
Vulkan: Default to 1GB allocations instead of 4GB to avoid fragmentation and driver issues (#12434)
|
hai 10 meses |
|
Łukasz Ślusarczyk
|
a53f7f7b88
fixed compilation warnings in ggml-sycl (#12424)
|
hai 10 meses |
 Molly Sophia
|
7dfad387e3
llama: Add support for RWKV v7 architecture (#12412)
|
hai 10 meses |
 Sigbjørn Skjæret
|
60c902926c
docs : bring llama-cli conversation/template docs up-to-date (#12426)
|
hai 10 meses |
 Gaurav Garg
|
b1b132efcb
cuda : enable CUDA Graph on CUDA Toolkit < 12.x (#12394)
|
hai 10 meses |
 Guus Waals
|
01e8f2138b
ggml-vulkan: remove unused find_program(glslc) (#12416)
|
hai 10 meses |
 Jeff Bolz
|
484a8ab513
vulkan: Add N/2 and N/4 optimized paths in coopmat2 shader (#12312)
|
hai 10 meses |
 Daniele
|
cf2270e4d3
vulkan: subgroup size tuning (#12087)
|
hai 10 meses |
|
Jeff Bolz
|
f07690c930
vulkan: use fp32 in coopmat2 q4_k dequant function (#12309)
|
hai 10 meses |
|
Jeff Bolz
|
891c63956d
vulkan: Pad N dimension of B matrix for coopmat2 perf, to avoid bounds checking (#12273)
|
hai 10 meses |
|
Jeff Bolz
|
2f21123c1d
vulkan: Adjust coopmat2 tile sizes and selection heuristic (#12258)
|
hai 10 meses |
 Christian Kastner
|
374101fd74
cmake : enable building llama.cpp using system libggml (#12321)
|
hai 10 meses |
 Akarshan Biswas
|
b3c9a65673
SYCL: set extras only on GGML_TYPE_Q4_0 (#12366)
|
hai 10 meses |
|
Sigbjørn Skjæret
|
8ba95dca20
llama : fix OLMo-2-0325-32B-Instruct K-norm size (#12400)
|
hai 10 meses |
|
Georgi Gerganov
|
dc079cfdff
context : fix init of n_outputs (#12397)
|
hai 10 meses |
 Daniel Bevenius
|
7b61bcc87c
ci : add --symlinks to xcframework zip command (#12409)
|
hai 10 meses |
 marcoStocchi
|
f4c3dd5daa
llama-tts : add '-o' option (#12398)
|
hai 10 meses |
 aubreyli
|
3d35d87b41
SYCL: Delete redundant plus sign and space (#12391)
|
hai 10 meses |
 fairydreaming
|
b19bd064c0
SYCL : support non-contiguous tensors in binary ops (add, sub, etc) (#12399)
|
hai 10 meses |
 Chenguang Li
|
92a391327e
[CANN]MUL_MAT optimization (#12382)
|
hai 10 meses |
 Eric Curtin
|
9f2250ba72
Add CLI arg to llama-run to adjust the number of threads used (#12370)
|
hai 10 meses |
