Georgi Gerganov
|
9cab53c7dd
|
cont : migrate the rest of the inputs out of llama_context
ggml-ci
|
2025-02-28 18:01:25 +02:00 |
|
Georgi Gerganov
|
7f02ee562e
|
context : decouple inputs, llama_graph_i become const (WIP)
ggml-ci
|
2025-02-28 16:30:41 +02:00 |
|
Georgi Gerganov
|
38db8a5861
|
llama : introduce concept of llama_memory
ggml-ci
|
2025-02-28 10:51:17 +02:00 |
|
Georgi Gerganov
|
828effd9d7
|
kv-cache : basic abstraction
ggml-ci
|
2025-02-27 16:00:29 +02:00 |
|
Georgi Gerganov
|
952feedfca
|
context : disable encoder embd tensor for now
ggml-ci
|
2025-02-27 15:07:10 +02:00 |
|
Georgi Gerganov
|
4efe989886
|
context : pass embeddings tensor from encoder to decoder
ggml-ci
|
2025-02-25 16:11:17 +02:00 |
|
Georgi Gerganov
|
e2b3294f2c
|
context : fix enc-dec state save/load
ggml-ci
|
2025-02-25 12:14:34 +02:00 |
|
Georgi Gerganov
|
be58e30017
|
enc-dec : compose wip
ggml-ci
|
2025-02-24 18:12:24 +02:00 |
|
Georgi Gerganov
|
9cd78f11a1
|
context : explicit llama_context_i abstract interface
ggml-ci
|
2025-02-24 13:38:11 +02:00 |
|
Georgi Gerganov
|
4a1054b552
|
context : reuse built_attn_mha
ggml-ci
|
2025-02-24 11:29:52 +02:00 |
|
Georgi Gerganov
|
a5a85a3bc0
|
context : fix recurrent reserve
ggml-ci
|
2025-02-24 08:59:12 +02:00 |
|
Georgi Gerganov
|
0699a44c83
|
context : remove redundant virtual, protected -> private
ggml-ci
|
2025-02-23 20:02:11 +02:00 |
|
Georgi Gerganov
|
6378112cb5
|
graph : remove the build_kv_... API from llama_graph_i
ggml-ci
|
2025-02-23 19:39:22 +02:00 |
|
Georgi Gerganov
|
372fa3a894
|
cont : enc should work now, next is dec
ggml-ci
|
2025-02-23 12:20:23 +02:00 |
|
Georgi Gerganov
|
f5e80208c5
|
wip enc-dec
|
2025-02-21 19:17:47 +02:00 |
|
Georgi Gerganov
|
3753b30d65
|
context : fix n_outputs init
ggml-ci
|
2025-02-21 15:53:26 +02:00 |
|
Georgi Gerganov
|
f588a70da3
|
context : wrap input tensors in struct
ggml-ci
|
2025-02-21 15:09:28 +02:00 |
|
Georgi Gerganov
|
ebf1bdf97b
|
context : add logs
ggml-ci
|
2025-02-21 14:35:23 +02:00 |
|
Georgi Gerganov
|
548c230dff
|
graph : remove worst_case from the API
ggml-ci
|
2025-02-21 13:29:25 +02:00 |
|
Georgi Gerganov
|
2645a7d9a9
|
context : add save/load for recurrent context
ggml-ci
|
2025-02-21 10:28:42 +02:00 |
|
Georgi Gerganov
|
08011c2ca1
|
context : add llama_kv_cache_recurrent prototype
ggml-ci
|
2025-02-20 20:55:13 +02:00 |
|
Georgi Gerganov
|
ad870c49f4
|
context : fix causal input for cache-less case
ggml-ci
|
2025-02-20 20:01:02 +02:00 |
|
Georgi Gerganov
|
b1554be1d7
|
context : add cache-less llama_context
ggml-ci
|
2025-02-20 18:30:04 +02:00 |
|
Georgi Gerganov
|
f95b04a21c
|
model : fix order kvq -> qkv
ggml-ci
|
2025-02-19 18:52:20 +02:00 |
|
Georgi Gerganov
|
2eacb4c1bf
|
graph : simplify attention api
ggml-ci
|
2025-02-19 18:43:49 +02:00 |
|
Georgi Gerganov
|
e17e4b72d1
|
context : add llama_context_recurrent
ggml-ci
|
2025-02-19 16:07:27 +02:00 |
|
Georgi Gerganov
|
5f11a5502a
|
kv-cache : remove llama_kv_cache_i
|
2025-02-19 14:36:27 +02:00 |
|
Georgi Gerganov
|
f5cedbcaaa
|
kv-cache : prepare for abstraction
ggml-ci
|
2025-02-18 21:28:58 +02:00 |
|
Georgi Gerganov
|
2bffc2d514
|
model : pass llama_graph_i as ptr
ggml-ci
|
2025-02-18 14:57:26 +02:00 |
|
Georgi Gerganov
|
9e50456e19
|
context : minor simplify
ggml-ci
|
2025-02-18 14:53:02 +02:00 |
|
Georgi Gerganov
|
befe14f06f
|
llama : reorder encode/decode in sources
|
2025-02-18 14:47:53 +02:00 |
|
Georgi Gerganov
|
bc6f187e9c
|
cont : use returend tensors from the graph build
ggml-ci
|
2025-02-18 14:24:17 +02:00 |
|
Georgi Gerganov
|
172f61690c
|
cont : return important tensors
ggml-ci
|
2025-02-18 13:48:43 +02:00 |
|
Georgi Gerganov
|
c23590319a
|
graph : add llama_graph_result
ggml-ci
|
2025-02-18 13:48:21 +02:00 |
|
Georgi Gerganov
|
1d801d27b9
|
graph : update attn/kv_self names
|
2025-02-14 17:22:55 +02:00 |
|
Georgi Gerganov
|
828064564c
|
context : move common inputs to base class
ggml-ci
|
2025-02-14 16:48:21 +02:00 |
|
Georgi Gerganov
|
d5e8e1a2ba
|
context : remove batch_manager
ggml-ci
|
2025-02-14 16:10:55 +02:00 |
|
Georgi Gerganov
|
131743ff4f
|
context : abstract constructor and init
ggml-ci
|
2025-02-13 17:17:51 +02:00 |
|
Georgi Gerganov
|
ed3cb55abe
|
context : abstract input
ggml-ci
|
2025-02-13 15:53:15 +02:00 |
|
Georgi Gerganov
|
107d1e2c32
|
context : move output functionality to base class
ggml-ci
|
2025-02-13 15:42:14 +02:00 |
|
Georgi Gerganov
|
e08f38df69
|
context : minor cleanup
ggml-ci
|
2025-02-13 12:50:53 +02:00 |
|
Georgi Gerganov
|
f7c7757bab
|
context : abstract state read/write
ggml-ci
|
2025-02-13 12:37:28 +02:00 |
|
Georgi Gerganov
|
3a504d9a0b
|
llama : introduce llama_io interfaces
ggml-ci
|
2025-02-13 12:25:54 +02:00 |
|
Georgi Gerganov
|
fbe6a07256
|
context : rename to llama_context_kv_self
|
2025-02-12 17:16:44 +02:00 |
|
Georgi Gerganov
|
6ee86e5e0f
|
graph : restore ubatch in build_cb
ggml-ci
|
2025-02-12 16:29:15 +02:00 |
|
Georgi Gerganov
|
f63aeecce6
|
llama : models now build their graphs using llama_graph_i
ggml-ci
|
2025-02-12 15:08:40 +02:00 |
|
Georgi Gerganov
|
5eae8e5183
|
context : move build_rope_factors to base class
ggml-ci
|
2025-02-12 13:32:02 +02:00 |
|
Georgi Gerganov
|
d146a14f77
|
context : minor naming fix
|
2025-02-12 12:41:36 +02:00 |
|
Georgi Gerganov
|
8da7f612b7
|
context : improve llama_context encapsulation
ggml-ci
|
2025-02-12 12:15:04 +02:00 |
|
Georgi Gerganov
|
b52b79b048
|
context : move encode/decode to llama-context.cpp
|
2025-02-12 11:23:38 +02:00 |