vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2026-04-29 20:29:48 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

[feature] release 0.1.3

Browse source
This commit is contained in:
chenxl 2024-08-28 16:11:43 +00:00
parent 67f8b370c3
commit 4d1d561d28
58 changed files with 11709 additions and 374 deletions
Download patch file Download diff file Expand all files Collapse all files

28
ktransformers/optimize/optimize_rules/Internlm2_5-7b-Chat-1m.yaml Normal file
View file

@ -0,0 +1,28 @@
- match:
class: ktransformers.models.modeling_llama.LlamaRotaryEmbedding
replace:
class: ktransformers.operators.RoPE.RotaryEmbeddingV2
- match:
name: "^model.embed_tokens"
replace:
class: "default"
kwargs:
generate_device: "cpu"
prefill_device: "cpu"
- match:
class: ktransformers.models.modeling_llama.LlamaModel
replace:
class: ktransformers.operators.models.KLlamaModel
kwargs:
generate_device: "cuda"
prefill_device: "cuda"
per_layer_prefill_intput_threshold: 0 # 0 is close layer wise prefill
- match:
name: "^model\\.layers\\..*\\.self_attn$"
replace:
class: ktransformers.operators.attention.KLlamaAttention
kwargs:
generate_device: "cuda"
prefill_device: "cuda"