 Georgi Gerganov
|
e0dbec0bc6
llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)
|
преди 10 месеца |
 theraininsky
|
a7b8ce2260
llama-bench : fix unexpected global variable initialize sequence issue (#11832)
|
преди 11 месеца |
 Radoslav Gerganov
|
667d72846c
rpc : early register backend devices (#11262)
|
преди 1 година |
|
Georgi Gerganov
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
преди 1 година |
|
Georgi Gerganov
|
47182dd03f
llama : update llama_model API names (#11063)
|
преди 1 година |
 Diego Devesa
|
cb13ef85a4
remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797)
|
преди 1 година |
|
Diego Devesa
|
5931c1f233
ggml : add support for dynamic loading of backends (#10469)
|
преди 1 година |
|
Diego Devesa
|
fab5d30ff6
llama : add .clang-format file (#10415)
|
преди 1 година |
|
Diego Devesa
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
преди 1 година |
|
Georgi Gerganov
|
841f27abdb
metal : optimize FA kernels (#10171)
|
преди 1 година |
|
Diego Devesa
|
c5b0f4b5d9
llama : refactor model loader with backend registry (#10026)
|
преди 1 година |
 Xuan Son Nguyen
|
cda0e4b648
llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745)
|
преди 1 година |
 Ouadie EL FAROUKI
|
87421a23e8
[SYCL] Add SYCL Backend registry, device and Event Interfaces (#9705)
|
преди 1 година |
|
Diego Devesa
|
0e9f760eb1
rpc : add backend registry / device interfaces (#9812)
|
преди 1 година |
 Michael Podvitskiy
|
7be099fa81
llama-bench: correct argument parsing error message (#9524)
|
преди 1 година |
|
Georgi Gerganov
|
0abc6a2c25
llama : llama_perf + option to disable timings during decode (#9355)
|
преди 1 година |
|
Georgi Gerganov
|
df270ef745
llama : refactor sampling v2 (#9294)
|
преди 1 година |
 Aarni Koskela
|
134bc38ecf
llama-bench : log benchmark progress (#9287)
|
преди 1 година |
|
slaren
|
bdf314f38a
llama-bench : fix NUL terminators in CPU name (#9313)
|
преди 1 година |
|
Radoslav Gerganov
|
82e3b03c11
rpc : make RPC servers come first in the device list (#9296)
|
преди 1 година |
|
Aarni Koskela
|
8962422b1c
llama-bench : add JSONL (NDJSON) output mode (#9288)
|
преди 1 година |
 Faisal Zaghloul
|
42c76d1358
Threadpool: take 2 (#8672)
|
преди 1 година |
 Zhenwei Jin
|
506122d854
llama-bench : add support for getting cpu info on Windows (#8824)
|
преди 1 година |
|
slaren
|
2b1f616b20
ggml : reduce hash table reset cost (#8698)
|
преди 1 година |
 hipudding
|
1bdd8ae19f
[CANN] Add Ascend NPU backend (#6035)
|
преди 1 година |
|
Radoslav Gerganov
|
e65bbf606c
llama-bench : fix RPC indication (#7936)
|
преди 1 година |
|
slaren
|
f578b86b21
move BLAS to a separate backend (#6210)
|
преди 1 година |
 Johannes Gäßler
|
148995e5e5
llama-bench: more compact markdown tables (#7879)
|
преди 1 година |
|
Georgi Gerganov
|
1442677f92
common : refactor cli arg parsing (#7675)
|
преди 1 година |
|
Georgi Gerganov
|
554c247caf
ggml : remove OpenCL (#7735)
|
преди 1 година |
