 Xuan Son Nguyen
|
cda0e4b648
llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745)
|
il y a 1 an |
 Ouadie EL FAROUKI
|
87421a23e8
[SYCL] Add SYCL Backend registry, device and Event Interfaces (#9705)
|
il y a 1 an |
 Diego Devesa
|
0e9f760eb1
rpc : add backend registry / device interfaces (#9812)
|
il y a 1 an |
 Michael Podvitskiy
|
7be099fa81
llama-bench: correct argument parsing error message (#9524)
|
il y a 1 an |
 Georgi Gerganov
|
0abc6a2c25
llama : llama_perf + option to disable timings during decode (#9355)
|
il y a 1 an |
|
Georgi Gerganov
|
df270ef745
llama : refactor sampling v2 (#9294)
|
il y a 1 an |
 Aarni Koskela
|
134bc38ecf
llama-bench : log benchmark progress (#9287)
|
il y a 1 an |
|
slaren
|
bdf314f38a
llama-bench : fix NUL terminators in CPU name (#9313)
|
il y a 1 an |
 Radoslav Gerganov
|
82e3b03c11
rpc : make RPC servers come first in the device list (#9296)
|
il y a 1 an |
|
Aarni Koskela
|
8962422b1c
llama-bench : add JSONL (NDJSON) output mode (#9288)
|
il y a 1 an |
 Faisal Zaghloul
|
42c76d1358
Threadpool: take 2 (#8672)
|
il y a 1 an |
 Zhenwei Jin
|
506122d854
llama-bench : add support for getting cpu info on Windows (#8824)
|
il y a 1 an |
|
slaren
|
2b1f616b20
ggml : reduce hash table reset cost (#8698)
|
il y a 1 an |
 hipudding
|
1bdd8ae19f
[CANN] Add Ascend NPU backend (#6035)
|
il y a 1 an |
|
Radoslav Gerganov
|
e65bbf606c
llama-bench : fix RPC indication (#7936)
|
il y a 1 an |
|
slaren
|
f578b86b21
move BLAS to a separate backend (#6210)
|
il y a 1 an |
 Johannes Gäßler
|
148995e5e5
llama-bench: more compact markdown tables (#7879)
|
il y a 1 an |
|
Georgi Gerganov
|
1442677f92
common : refactor cli arg parsing (#7675)
|
il y a 1 an |
|
Georgi Gerganov
|
554c247caf
ggml : remove OpenCL (#7735)
|
il y a 1 an |
|
slaren
|
adc9ff3841
llama-bench : allow using a different printer for stderr with -oe (#7722)
|
il y a 1 an |
|
Radoslav Gerganov
|
210d99173d
llama-bench : add support for the RPC backend (#7435)
|
il y a 1 an |
|
Georgi Gerganov
|
6ff13987ad
common : normalize naming style (#7462)
|
il y a 1 an |
|
slaren
|
b18532a4ef
phi3 : duplicate rope factors in each layer (#7447)
|
il y a 1 an |
|
slaren
|
e849648888
llama-bench : add pp+tg test type (#7199)
|
il y a 1 an |
 kunnis
|
628b299106
Adding support for the --numa argument for llama-bench. (#7080)
|
il y a 1 an |
|
Georgi Gerganov
|
9c67c2773d
ggml : add Flash Attention (#5021)
|
il y a 1 an |
 Justine Tunney
|
8cc91dc63c
ggml : add llamafile sgemm (#6414)
|
il y a 1 an |
|
slaren
|
280345968d
cuda : rename build flag to LLAMA_CUDA (#6299)
|
il y a 1 an |
 Kawrakow
|
76aa30a263
Add ability to use Q5_0, Q5_1, and IQ4_NL for quantized K cache (#6183)
|
il y a 1 an |
|
slaren
|
2bf8d0f7c4
backend : offload large batches to GPU (#6083)
|
il y a 1 an |
