423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2026-08-17 13:35:44 +08:00
Code Issues Packages Projects Releases Wiki Activity

[train] Harden KTransformers MoE LoRA SFT integration (#10738)

Browse Source
This commit is contained in:
yyj
2026-08-13 20:43:15 +08:00
committed by GitHub
parent 199b8873d7
commit bc4b42cefc
17 changed files with 573 additions and 101 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
examples/ktransformers/accelerate/fsdp2_kt_bf16.yaml
View File

@@ -13,13 +13,3 @@ num_processes: 4 # Adjust based on your GPU count; 4 is suitable for 4 GPUs
rdzv_backend: static
same_network: true
use_cpu: false
kt_config:
enabled: true
kt_backend: AMXBF16 # Use with original BF16 expert weights.
kt_num_threads: 96
kt_tp_enabled: true
kt_threadpool_count: 2
kt_max_cache_depth: 2
kt_share_backward_bb: true
lora_rank: 8

10
examples/ktransformers/accelerate/fsdp2_kt_int4.yaml
View File

@@ -13,13 +13,3 @@ num_processes: 4 # Adjust based on your GPU count; 4 is suitable for 4 GPUs
rdzv_backend: static
same_network: true
use_cpu: false
kt_config:
enabled: true
kt_backend: AMXINT4 # Use with online-converted INT4 expert weights
kt_num_threads: 96
kt_tp_enabled: true
kt_threadpool_count: 2
kt_max_cache_depth: 2
kt_share_backward_bb: true
lora_rank: 8

10
examples/ktransformers/accelerate/fsdp2_kt_int8.yaml
View File

@@ -13,13 +13,3 @@ num_processes: 4 # Adjust based on your GPU count; 4 is suitable for 4 GPUs
rdzv_backend: static
same_network: true
use_cpu: false
kt_config:
enabled: true
kt_backend: AMXINT8 # Use with online-converted INT8 expert weights
kt_num_threads: 96
kt_tp_enabled: true
kt_threadpool_count: 2
kt_max_cache_depth: 2
kt_share_backward_bb: true
lora_rank: 8

10
examples/ktransformers/accelerate/fsdp2_kt_int8_1gpu.yaml
View File

@@ -13,13 +13,3 @@ num_processes: 1 # Adjust based on your GPU count; 1 is suitable for 1 GPU
rdzv_backend: static
same_network: true
use_cpu: false
kt_config:
enabled: true
kt_backend: AMXINT8 # Use with online-converted INT8 expert weights
kt_num_threads: 96
kt_tp_enabled: true
kt_threadpool_count: 2
kt_max_cache_depth: 2
kt_share_backward_bb: true
lora_rank: 8

10
examples/ktransformers/accelerate/fsdp2_kt_int8_8gpu.yaml
View File

@@ -13,13 +13,3 @@ num_processes: 8 # Adjust based on your GPU count; 8 is suitable for 8 GPUs
rdzv_backend: static
same_network: true
use_cpu: false
kt_config:
enabled: true
kt_backend: AMXINT8 # Use with online-converted INT8 expert weights
kt_num_threads: 96
kt_tp_enabled: true
kt_threadpool_count: 2
kt_max_cache_depth: 2
kt_share_backward_bb: true
lora_rank: 8