vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-07 21:19:51 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix typo in README.md

Browse source
This commit is contained in:
cuichengyi 2025-02-13 10:12:04 +08:00
parent a0c16db352
commit 01655f7500
2 changed files with 5 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
README.md
View file

@ -43,10 +43,10 @@ https://github.com/user-attachments/assets/ebd70bfa-b2c1-4abb-ae3b-296ed38aa285
- **[NEW!!!] Local 671B DeepSeek-Coder-V3/R1:** Running its Q4_K_M version using only 14GB VRAM and 382GB DRAM([Tutorial](./doc/en/DeepseekR1_V3_tutorial.md)).
- Prefill Speed (tokens/s):
- KTransfermor: 54.21 (32 cores) → 74.362 (dual-socket, 2×32 cores) → 255.26 (optimized AMX-based MoE kernel, V0.3 only) → 286.55 (selectively using 6 experts, V0.3 only)
- KTransformers: 54.21 (32 cores) → 74.362 (dual-socket, 2×32 cores) → 255.26 (optimized AMX-based MoE kernel, V0.3 only) → 286.55 (selectively using 6 experts, V0.3 only)
- Compared to 10.31 tokens/s in llama.cpp with 2×32 cores, achieving up to **27.79× speedup**.
- Decode Speed (tokens/s):
- KTransfermor: 8.73 (32 cores) → 11.26 (dual-socket, 2×32 cores) → 13.69 (selectively using 6 experts, V0.3 only)
- KTransformers: 8.73 (32 cores) → 11.26 (dual-socket, 2×32 cores) → 13.69 (selectively using 6 experts, V0.3 only)
- Compared to 4.51 tokens/s in llama.cpp with 2×32 cores, achieving up to **3.03× speedup**.
- Upcoming Open Source Release:
- AMX optimizations and selective expert activation will be open-sourced in V0.3.

6
doc/en/DeepseekR1_V3_tutorial.md
View file

@ -39,10 +39,10 @@ https://github.com/user-attachments/assets/ebd70bfa-b2c1-4abb-ae3b-296ed38aa285
- **[NEW!!!] Local 671B DeepSeek-Coder-V3/R1:** Running its Q4_K_M version using only 14GB VRAM and 382GB DRAM.
- Prefill Speed (tokens/s):
- KTransfermor: 54.21 (32 cores) → 74.362 (dual-socket, 2×32 cores) → 255.26 (optimized AMX-based MoE kernel, V0.3 only) → 286.55 (selectively using 6 experts, V0.3 only)
- KTransformers: 54.21 (32 cores) → 74.362 (dual-socket, 2×32 cores) → 255.26 (optimized AMX-based MoE kernel, V0.3 only) → 286.55 (selectively using 6 experts, V0.3 only)
- Compared to 10.31 tokens/s in llama.cpp with 2×32 cores, achieving up to **27.79× speedup**.
- Decode Speed (tokens/s):
- KTransfermor: 8.73 (32 cores) → 11.26 (dual-socket, 2×32 cores) → 13.69 (selectively using 6 experts, V0.3 only)
- KTransformers: 8.73 (32 cores) → 11.26 (dual-socket, 2×32 cores) → 13.69 (selectively using 6 experts, V0.3 only)
- Compared to 4.51 tokens/s in llama.cpp with 2×32 cores, achieving up to **3.03× speedup**.
@ -175,4 +175,4 @@ Intel is currently the only CPU vendor that supports AMX-like instructions, whic
Attention! If you are testing R1 and it may skip thinking. So you can add arg: `--force_think true`. The detail is in [FAQ](./FAQ.md) part <br>
### More FAQ
[See detail](./FAQ.md)
[See detail](./FAQ.md)