Alex Barron 85ffd2c96a Quantized KV Cache (#1075) ...

* add QuantizedKVCache

* simplify

* add tests

* single sdpa function

* fix sed

* in place

* fix tests

* support different k and v head dims

2024-10-31 16:59:52 -07:00

..

__init__.py

Mlx llm package (#301)

2024-01-12 10:25:56 -08:00

base.py

Quantized KV Cache (#1075)

2024-10-31 16:59:52 -07:00

cache.py

Quantized KV Cache (#1075)

2024-10-31 16:59:52 -07:00

cohere.py

Quantized KV Cache (#1075)

2024-10-31 16:59:52 -07:00

dbrx.py

Quantized KV Cache (#1075)

2024-10-31 16:59:52 -07:00

deepseek_v2.py

Quantized KV Cache (#1075)

2024-10-31 16:59:52 -07:00

deepseek.py

Quantized KV Cache (#1075)

2024-10-31 16:59:52 -07:00

gemma2.py

override dtype with quant (#1062)

2024-10-22 09:56:45 -07:00

gemma.py

Quantized KV Cache (#1075)

2024-10-31 16:59:52 -07:00

gpt2.py

Quantized KV Cache (#1075)

2024-10-31 16:59:52 -07:00

gpt_bigcode.py

Quantized KV Cache (#1075)

2024-10-31 16:59:52 -07:00

gpt_neox.py

Quantized KV Cache (#1075)

2024-10-31 16:59:52 -07:00

internlm2.py

Quantized KV Cache (#1075)

2024-10-31 16:59:52 -07:00

llama.py

Quantized KV Cache (#1075)

2024-10-31 16:59:52 -07:00

mamba.py

fix mamba models conversion (#1065)

2024-10-22 15:44:08 -07:00

minicpm.py

Quantized KV Cache (#1075)

2024-10-31 16:59:52 -07:00

mixtral.py

Quantized KV Cache (#1075)

2024-10-31 16:59:52 -07:00

nemotron.py

Quantized KV Cache (#1075)

2024-10-31 16:59:52 -07:00

olmo.py

More cache improvements (#1015)

2024-10-07 20:45:51 -07:00

openelm.py

Quantized KV Cache (#1075)

2024-10-31 16:59:52 -07:00

phi3.py

Quantized KV Cache (#1075)

2024-10-31 16:59:52 -07:00

phi3small.py

Quantized KV Cache (#1075)

2024-10-31 16:59:52 -07:00

phi.py

Quantized KV Cache (#1075)

2024-10-31 16:59:52 -07:00

phimoe.py

Quantized KV Cache (#1075)

2024-10-31 16:59:52 -07:00

phixtral.py

Quantized KV Cache (#1075)

2024-10-31 16:59:52 -07:00

plamo.py

Quantized KV Cache (#1075)

2024-10-31 16:59:52 -07:00

qwen2_moe.py

Quantized KV Cache (#1075)

2024-10-31 16:59:52 -07:00

qwen2.py

Quantized KV Cache (#1075)

2024-10-31 16:59:52 -07:00

qwen.py

Quantized KV Cache (#1075)

2024-10-31 16:59:52 -07:00

recurrent_gemma.py

Quantized KV Cache (#1075)

2024-10-31 16:59:52 -07:00

stablelm.py

Quantized KV Cache (#1075)

2024-10-31 16:59:52 -07:00

starcoder2.py

Quantized KV Cache (#1075)

2024-10-31 16:59:52 -07:00

su_rope.py

Add Phi-3.5-MoE (#946)

2024-08-24 06:52:33 -07:00

switch_layers.py

Handle longer prompt/generation (#931)

2024-08-16 15:28:39 -07:00