llama.cpp

mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-05 02:23:54 +00:00

Files

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

test_basic.py

…

test_chat_completion.py

server: fix deadly typo in response_format.json_schema.schema handling (#12168 )

2025-03-04 08:24:07 +02:00

test_completion.py

server : Fixed wrong function name in llamacpp server unit test (#11473 )

2025-01-29 00:03:42 +01:00

test_ctx_shift.py

…

test_embedding.py

llama : fix FA when KV cache is not used (i.e. embeddings) (#12825 )

2025-04-08 19:54:51 +03:00

test_infill.py

server : fix extra BOS in infill endpoint (#11106 )

2025-01-06 15:36:08 +02:00

test_lora.py

server : allow using LoRA adapters per-request (#10994 )

2025-01-02 15:05:18 +01:00

test_rerank.py

server : add TEI API format for /rerank endpoint (#11942 )

2025-02-18 14:21:41 +01:00

test_security.py

…

test_slot_save.py

…

test_speculative.py

server : allow using LoRA adapters per-request (#10994 )

2025-01-02 15:05:18 +01:00

test_tokenize.py

…

test_tool_call.py

tool-call: ensure there's always a non-empty tool call id (#12292 )

2025-03-10 09:45:29 +00:00