diff --git a/.gitignore b/.gitignore
index 5d72e80..1bb8666 100644
--- a/.gitignore
+++ b/.gitignore
@@ -17,5 +17,4 @@ compile_commands.json
*dist/
ktransformers/server/local_store/
ktransformers/server_test1.db
-*.patch
-local_chat_djw.py
\ No newline at end of file
+*.patch
\ No newline at end of file
diff --git a/README.md b/README.md
index a3a6792..6800009 100644
--- a/README.md
+++ b/README.md
@@ -24,7 +24,7 @@ Our vision for KTransformers is to serve as a flexible platform for experimentin
🔥 Updates
* **Aug 28, 2024**: Support 1M context under the InternLM2.5-7B-Chat-1M model, utilizing 24GB of VRAM and 150GB of DRAM.
-* **Aug 28, 2024**: Decrease DeepseekV2's required DRAM from 20G to 10G.
+* **Aug 28, 2024**: Decrease DeepseekV2's required VRAM from 21G to 11G.
* **Aug 15, 2024**: Update detailed [TUTORIAL](doc/en/injection_tutorial.md) for injection and multi-GPU.
* **Aug 14, 2024**: Support llamfile as linear backend.
* **Aug 12, 2024**: Support multiple GPU; Support new model: mixtral 8\*7B and 8\*22B; Support q2k, q3k, q5k dequant on gpu.
@@ -62,7 +62,7 @@ https://github.com/user-attachments/assets/0b9fa2da-66f0-48eb-b4b9-f0e1f06f8927
-- **Local 236B DeepSeek-Coder-V2:** Running its Q4_K_M version using only 21GB VRAM and 136GB DRAM, attainable on a local desktop machine, which scores even better than GPT4-0613 in [BigCodeBench](https://huggingface.co/blog/leaderboard-bigcodebench).
+- **Local 236B DeepSeek-Coder-V2:** Running its Q4_K_M version using only 11GB VRAM and 136GB DRAM, attainable on a local desktop machine, which scores even better than GPT4-0613 in [BigCodeBench](https://huggingface.co/blog/leaderboard-bigcodebench).
@@ -215,7 +215,7 @@ It features the following arguments:
| Model Name | Model Size | VRAM | Minimum DRAM | Recommended DRAM |
| ------------------------------ | ---------- | ----- | --------------- | ----------------- |
-| DeepSeek-V2-q4_k_m | 133G | 10G | 136G | 192G |
+| DeepSeek-V2-q4_k_m | 133G | 11G | 136G | 192G |
| Qwen2-57B-A14B-Instruct-q4_k_m | 33G | 8G | 34G | 64G |
| DeepSeek-V2-Lite-q4_k_m | 9.7G | 3G | 13G | 16G |
| Mixtral-8x7B-q4_k_m | 25G | 1.6G | 51G | 64G |
diff --git a/ktransformers/optimize/optimize_rules/DeepSeek-V2-Chat.yaml b/ktransformers/optimize/optimize_rules/DeepSeek-V2-Chat.yaml
index 52db7dd..b115aba 100644
--- a/ktransformers/optimize/optimize_rules/DeepSeek-V2-Chat.yaml
+++ b/ktransformers/optimize/optimize_rules/DeepSeek-V2-Chat.yaml
@@ -46,7 +46,7 @@
replace:
class: "ktransformers.operators.models.KDeepseekV2Model"
kwargs:
- per_layer_prefill_intput_threshold: 2000 # 0 is close layer wise prefill
+ per_layer_prefill_intput_threshold: 0 # 0 is close layer wise prefill
- match:
name: "^model.embed_tokens"
replace: