Nexes the Elder 39e712620d Streamline a bit the quant strategies (#443) ...

* Streamline a bit the quant strategies

No change over the existing patterns, except for the bump for attn_k and attn_v for the models with 4 and 6 experts (several frankensteins seen on HF, and which also use GQA).
The rest is applying the existing patterns to the new IQ_K quants.
Also, a Q8_0 for attn_q slipped into the MOEs 8 experts rule, I removed it, because that tensor is much bigger than attn_k or attn_v.

* remove <=8 experts condition.

2025-05-22 18:04:47 +03:00

..

CMakeLists.txt

Be able to repack tensors at run time (#147)

2024-12-17 14:16:34 +01:00

llama-grammar.cpp

Merge mainline - Aug 12 2024 (#17)

2024-08-12 15:14:32 +02:00

llama-grammar.h

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

llama-impl.h

Add copyright notices (#317)

2025-04-07 10:43:26 +02:00

llama-sampling.cpp

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

llama-sampling.h

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

llama-vocab.cpp

LlaMA-4 support (text only) (#321)

2025-04-10 09:05:21 +02:00

llama-vocab.h

Merge mainline - Aug 12 2024 (#17)

2024-08-12 15:14:32 +02:00

llama.cpp

Streamline a bit the quant strategies (#443)

2025-05-22 18:04:47 +03:00

unicode-data.cpp

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

unicode-data.h

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

unicode.cpp

Deepseek V3 support added (#176)

2025-01-23 18:24:10 +02:00

unicode.h

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00