Skip to content

fix: remove virtual allocation from DeepSeek key takeaways #83

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
solderzzc merged 1 commit into from
Apr 24, 2026
Merged

fix: remove virtual allocation from DeepSeek key takeaways #83

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,9 +88,9 @@ Model: [`Thump604/DeepSeek-V4-Flash-MLX-Q3-mixed-gs128-affine`](https://huggingf
> Values shown as `generation speed · peak physical RAM used` (sampled every 0.5s during prefill + generation). The 126 GB model streams the rest from NVMe SSD.

**Key takeaways:**
- 🏆 **SSD + TurboQuant dominates at long context** — 4.16 tok/s at 40K vs 0.32 tok/s for plain SSD Stream (**13× faster**), with 33% lower GPU allocation (40.6 GB vs 60.5 GB).
- 🏆 **SSD + TurboQuant dominates at long context** — 4.16 tok/s at 40K vs 0.32 tok/s for plain SSD Stream (**13× faster**). TurboQuant compresses the KV cache so far fewer layers need to stream from SSD per token.
- At 512-token context all configurations perform similarly (~4.4–4.8 tok/s); TurboQuant's advantage is KV-cache compression at long context.
Copy link

Copilot AI Apr 24, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

In this Key takeaways section, the terminology is inconsistent between “KV cache” (line 91) and “KV-cache” (line 92). Please standardize the phrasing (pick one form) within the section for readability/searchability.

Suggested change
- At 512-token context all configurations perform similarly (~4.4–4.8 tok/s); TurboQuant's advantage is KV-cache compression at long context.
- At 512-token context all configurations perform similarly (~4.4–4.8 tok/s); TurboQuant's advantage is KV cache compression at long context.

Copilot uses AI. Check for mistakes.
- Peak physical RAM (GPU InUse) stays ≤ 17 GB across all configurations — the rest streams from NVMe SSD.
- Peak physical RAM stays ≤ 17 GB across all configurations — the 126 GB model streams the rest from NVMe SSD.

---

Expand Down
Loading