vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-05 20:19:51 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

⚡ fix typo readme

Browse source
This commit is contained in:
liam 2025-02-10 11:36:46 +08:00
parent 0f73f40da0
commit aecb50f0d1
2 changed files with 6 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
README.md
View file

@ -43,13 +43,13 @@ 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:
- KTransfermor: 54.21 (32 cores) → 74.362 (dual-socket, 2×32 cores) → 255.26 (optimized AMX-based MoE kernel, v3 only) → 286.55 (selectively using 6 experts, v3 only)
- 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)
- Compared to 4.51 tokens/s in llama.cpp with 2×32 cores, achieving up to **63.53× speedup**.
- Decode Speed(tokens/s):
- KTransfermor: 8.73 (32 cores) → 11.26 (dual-socket, 2×32 cores) → 13.69 (selectively using 6 experts, v3 only)
- KTransfermor: 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.
- AMX optimizations and selective expert activation will be open-sourced in V0.3.
- Currently available only in preview binary distribution, which can be found [here](xxx).
- **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).

6
doc/en/DeepseekR1_V3_tutorial.md
View file

@ -7,13 +7,13 @@ 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:
- KTransfermor: 54.21 (32 cores) → 74.362 (dual-socket, 2×32 cores) → 255.26 (optimized AMX-based MoE kernel, v3 only) → 286.55 (selectively using 6 experts, v3 only)
- 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)
- Compared to 4.51 tokens/s in llama.cpp with 2×32 cores, achieving up to **63.53× speedup**.
- Decode Speed(tokens/s):
- KTransfermor: 8.73 (32 cores) → 11.26 (dual-socket, 2×32 cores) → 13.69 (selectively using 6 experts, v3 only)
- KTransfermor: 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.
- AMX optimizations and selective expert activation will be open-sourced in V0.3.
- Currently available only in preview binary distribution, which can be found [here](xxx).