Merge branch 'kvcache-ai:main' into main

877aec85 · Yuhao Tsui · GitHub · 84164f58 · 9037bf30 · 877aec85
Unverified Commit 877aec85 authored Apr 09, 2025 by Yuhao Tsui Committed by GitHub Apr 09, 2025
20 changed files
--- a/ktransformers/optimize/optimize_rules/DeepSeek-V3-Chat-multi-gpu.yaml
+++ b/ktransformers/optimize/optimize_rules/DeepSeek-V3-Chat-multi-gpu.yaml
--- a/ktransformers/optimize/optimize_rules/DeepSeek-V3-Chat-serve.yaml
+++ b/ktransformers/optimize/optimize_rules/DeepSeek-V3-Chat-serve.yaml
--- a/ktransformers/optimize/optimize_rules/DeepSeek-V3-Chat.yaml
+++ b/ktransformers/optimize/optimize_rules/DeepSeek-V3-Chat.yaml
--- a/ktransformers/optimize/optimize_rules/Moonlight-16B-A3B-serve.yaml
+++ b/ktransformers/optimize/optimize_rules/Moonlight-16B-A3B-serve.yaml
--- a/ktransformers/server/args.py
+++ b/ktransformers/server/args.py
--- a/ktransformers/server/backend/args.py
+++ b/ktransformers/server/backend/args.py
--- a/ktransformers/server/backend/context_manager.py
+++ b/ktransformers/server/backend/context_manager.py
--- a/ktransformers/server/backend/interfaces/balance_serve.py
+++ b/ktransformers/server/backend/interfaces/balance_serve.py
--- a/ktransformers/server/backend/interfaces/ktransformers.py
+++ b/ktransformers/server/backend/interfaces/ktransformers.py
--- a/ktransformers/server/backend/interfaces/transformers.py
+++ b/ktransformers/server/backend/interfaces/transformers.py
--- a/ktransformers/server/balance_serve/inference/__init__.py
+++ b/ktransformers/server/balance_serve/inference/__init__.py
--- a/ktransformers/server/balance_serve/inference/config.py
+++ b/ktransformers/server/balance_serve/inference/config.py
--- a/ktransformers/server/balance_serve/inference/distributed/__init__.py
+++ b/ktransformers/server/balance_serve/inference/distributed/__init__.py
--- a/ktransformers/server/balance_serve/inference/distributed/communication_op.py
+++ b/ktransformers/server/balance_serve/inference/distributed/communication_op.py
--- a/ktransformers/server/balance_serve/inference/distributed/cuda_wrapper.py
+++ b/ktransformers/server/balance_serve/inference/distributed/cuda_wrapper.py
--- a/ktransformers/server/balance_serve/inference/distributed/custom_all_reduce.py
+++ b/ktransformers/server/balance_serve/inference/distributed/custom_all_reduce.py
--- a/ktransformers/server/balance_serve/inference/distributed/custom_all_reduce_utils.py
+++ b/ktransformers/server/balance_serve/inference/distributed/custom_all_reduce_utils.py
--- a/ktransformers/server/balance_serve/inference/distributed/parallel_state.py
+++ b/ktransformers/server/balance_serve/inference/distributed/parallel_state.py
--- a/ktransformers/server/balance_serve/inference/distributed/pynccl.py
+++ b/ktransformers/server/balance_serve/inference/distributed/pynccl.py
--- a/ktransformers/server/balance_serve/inference/distributed/pynccl_wrapper.py
+++ b/ktransformers/server/balance_serve/inference/distributed/pynccl_wrapper.py