vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-15 17:49:42 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge pull request #795 from hybcloud/main

Browse source 
fix minor typo
This commit is contained in:
Atream 2025-03-05 11:27:26 +08:00 • committed by GitHub
commit 3a3021502e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
doc/en/DeepseekR1_V3_tutorial.md
View file

@ -86,7 +86,7 @@ Memory: standard DDR5-4800 server DRAM (1 TB), each socket with 8×DDR5-4800
#### Change Log #### Change Log
- Longer Context (from 4K to 8K for 24GB VRAM) and Slightly Faster Speed （+15%):<br> - Longer Context (from 4K to 8K for 24GB VRAM) and Slightly Faster Speed （+15%):<br>
Integrated the highly efficient Triton MLA Kernel from the fantastic sglang project, enable much longer context length and slightly faster prefill/decode speed Integrated the highly efficient Triton MLA Kernel from the fantastic sglang project, enable much longer context length and slightly faster prefill/decode speed
- We suspect that some of the improvements come from the change of hardwre platform (4090D->4090) - We suspect that some of the improvements come from the change of hardware platform (4090D->4090)
#### Benchmark Results #### Benchmark Results