 Georgi Gerganov
|
254098a279
common : refactor common_sampler + grammar logic changes (#17937)
|
преди 1 месец |
|
Georgi Gerganov
|
2adf8d83ac
parallel : add option for different RNG seeds (#14757)
|
преди 6 месеца |
|
Georgi Gerganov
|
225e7a1438
llama : add high-throughput mode (#14363)
|
преди 6 месеца |
|
Georgi Gerganov
|
745aa5319b
llama : deprecate llama_kv_self_ API (#14030)
|
преди 7 месеца |
|
Georgi Gerganov
|
c04621711a
parallel : fix n_junk == 0 (#13952)
|
преди 7 месеца |
|
Georgi Gerganov
|
3f55f781f1
llama : auto-batch preparation (#13845)
|
преди 7 месеца |
|
Georgi Gerganov
|
12d0188c0d
kv-cache : refactor + add llama_memory_state_i (#13746)
|
преди 7 месеца |
|
Georgi Gerganov
|
dd665cc9d4
parallel : increase the variability of the prompt lengths (#13927)
|
преди 7 месеца |
|
Georgi Gerganov
|
a4090d1174
llama : remove llama_kv_cache_view API + remove deprecated (#13653)
|
преди 8 месеца |
|
Georgi Gerganov
|
518329b2d4
parallel : add option for non-shared and larger prompts (#13598)
|
преди 8 месеца |
|
Georgi Gerganov
|
a10b36c91a
llama : refactor kv cache guard (#12695)
|
преди 9 месеца |
 Xuan-Son Nguyen
|
267c1399f1
common : refactor downloading system, handle mmproj with -hf option (#12694)
|
преди 9 месеца |
|
Georgi Gerganov
|
e0dbec0bc6
llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)
|
преди 10 месеца |
 mgroeber9110
|
5bbe6a9fe9
ggml : portability fixes for VS 2017 (#12150)
|
преди 10 месеца |
|
Georgi Gerganov
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
преди 1 година |
|
Georgi Gerganov
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
преди 1 година |
|
Georgi Gerganov
|
d9d54e498d
speculative : refactor and add a simpler example (#10362)
|
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 |
 Diego Devesa
|
7eee341bee
common : use common_ prefix for common library functions (#9805)
|
преди 1 година |
|
Georgi Gerganov
|
6262d13e0b
common : reimplement logging (#9418)
|
преди 1 година |
|
Georgi Gerganov
|
0abc6a2c25
llama : llama_perf + option to disable timings during decode (#9355)
|
преди 1 година |
|
Xuan Son Nguyen
|
bfe76d4a17
common : move arg parser code to `arg.cpp` (#9388)
|
преди 1 година |
|
Xuan Son Nguyen
|
1b9ae5189c
common : refactor arg parser (#9308)
|
преди 1 година |
|
Georgi Gerganov
|
df270ef745
llama : refactor sampling v2 (#9294)
|
преди 1 година |
 Liu Jia
|
0a4ce78681
common : Changed tuple to struct (TODO fix) (#8823)
|
преди 1 година |
|
Georgi Gerganov
|
1442677f92
common : refactor cli arg parsing (#7675)
|
преди 1 година |
|
Georgi Gerganov
|
6ff13987ad
common : normalize naming style (#7462)
|
преди 1 година |
 Pedro Cuenca
|
b97bc3966e
llama : support Llama 3 HF conversion (#6745)
|
преди 1 година |
 compilade
|
557410b8f0
llama : greatly reduce output buffer memory usage (#6122)
|
преди 1 година |
|
compilade
|
c2101a2e90
llama : support Mamba Selective State Space Models (#5328)
|
преди 1 година |
