Georgi Gerganov
a19b5cef16
llama : fix FA when KV cache is not used (i.e. embeddings) ( #12825 )
...
* ggml : FA supports F32 V
* graph : cast KV to F16 when the KV cache is not used
ggml-ci
* server : add test that exercises embeddings with FA enabled
ggml-ci
2025-04-08 19:54:51 +03:00
Xuan-Son Nguyen
1466621e73
llama : Support llama 4 text-only ( #12791 )
...
* llama4 conversion
* initial support, no chat template
* clean up a bit
* fix tokenizer conversion
* correct hparams
* try this
* fix shexp
* ffn_inp_normed
* chat template
* clean up model conversion
* add_bos
* add scale_before_ffn
* fix order
* weight_before_ffn
* llm_graph_input_attn_temp
* add chunk attn mask
* build_inp_attn_scale()
* add comment about ggml_repeat
* clarify comments
* fix build
2025-04-07 23:06:44 +02:00
Xuan-Son Nguyen
af6ae1efb2
llama : fix non-causal mask for gemma 3 ( #12615 )
2025-03-30 00:07:37 +01:00
Georgi Gerganov
75422e8bc4
graph : normalize Q, K, V shapes + sync cross attention ( #12449 )
...
* graph : normalize Q, K, V shapes and add comments
ggml-ci
* context : synchronize before getting cross attention data
* model : fix command-r attention norm check
2025-03-18 21:35:19 +02:00
fairydreaming
8fcb563613
Load all MoE experts during warmup ( #11571 )
...
* llama : introduce llama_set_warmup() API call that controls warmup mode; use all MoE experts during warmup
* common : use new API to enable warmup mode during model warmup
---------
Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
2025-03-14 13:47:05 +01:00
Georgi Gerganov
c522ce4143
graph : simplify attn input build for unified KV cache ( #12381 )
...
ggml-ci
2025-03-14 10:47:44 +02:00
Georgi Gerganov
081bee8c64
hparams : add SWA rope parameters ( #12374 )
...
ggml-ci
2025-03-14 09:03:24 +02:00
Georgi Gerganov
84d5475541
llama : fix Gemma3 SWA KV cache shift ( #12373 )
...
* llama : fix Gemma3 SWA KV cache shift
ggml-ci
* hparams : add comment [no ci]
2025-03-13 19:08:07 +02:00
Georgi Gerganov
e0dbec0bc6
llama : refactor llama_context, llama_kv_cache, llm_build_context ( #12181 )
...
* llama : refactor llama_context, llama_kv_cache, llm_build_context
ggml-ci
* graph : don't mutate the KV cache during defrag
ggml-ci
* context : reduce virtuals + remove test function
ggml-ci
* context : move interface implementation to source file + factory
ggml-ci
* graph : move KV cache build functions to llama_context impl
ggml-ci
* graph : remove model reference from build_pooling
ggml-ci
* graph : remove llama_model reference
ggml-ci
* kv_cache : provide rope factors
ggml-ci
* graph : rework inputs to use only unique_ptr, remove attn input abstraction
ggml-ci
* context : remove llama_context_i abstraction
ggml-ci
* context : clean-up
ggml-ci
* graph : clean-up
ggml-ci
* llama : remove redundant keywords (struct, enum)
ggml-ci
* model : adapt gemma3
ggml-ci
* graph : restore same attention ops as on master
ggml-ci
* llama : remove TODO + fix indent
ggml-ci
2025-03-13 12:35:44 +02:00
