@quaid

Founder https://xitter.cf/t.co/XvGjzwaBya, ex-Red Hat, ex-VA LNX Cares deeply. Parent, survivor (again), & esp your brother. He/Him/ร‰l/They. All copyright works CC BY SA 4.0

 Santa Cruz, CA
iquaid.org
Joined March 2007
  • Tweets17.4K
  • Following1.3K
  • Followers1.3K
819Media
Donald Leon Wade, 23 Jan 1942 - 21 Dec 2021 Of his four sons, I had the fewest formative years w/him. But being his one biological son, his effect on me is as profound as for my brothers K*, T*, & A*. A little ๐Ÿงตabout Dad: scientist, storyteller, home chef, minister's hubby ...
This is a picture of me and my father, circa 1975, in original black & white. I appear about five years old, a white cis boy with straight nearly-white blond hair, bangs cut straight across above my eyebrows. I'm wearing a gray sweatshirt and overalls, probably Oshkosh brand. I'm sitting on my father's lap, one knee forward with foot underneath me, looking down-left toward the camera. My father's arms encircling me appear to be striking a match in front. He and I look much alike, as his only biological son, though his hair is shades darker here and longer, but of a similar shape, as well as nose and mouth and shape of our faces, are all similar. His beard is dark and a little grizzly, and clenched between his teeth is a brown-wood tobacco pipe. His bangs are grown in so the hair has to part above his glasses to see, putting his eyes partially in shadow. He wears a button-up shirt, the sleeves rolled up. Light pours through a window behind us, sitting near his student desk & coffee cup.

ALT This is a picture of me and my father, circa 1975, in original black & white. I appear about five years old, a white cis boy with straight nearly-white blond hair, bangs cut straight across above my eyebrows. I'm wearing a gray sweatshirt and overalls, probably Oshkosh brand. I'm sitting on my father's lap, one knee forward with foot underneath me, looking down-left toward the camera. My father's arms encircling me appear to be striking a match in front. He and I look much alike, as his only biological son, though his hair is shades darker here and longer, but of a similar shape, as well as nose and mouth and shape of our faces, are all similar. His beard is dark and a little grizzly, and clenched between his teeth is a brown-wood tobacco pipe. His bangs are grown in so the hair has to part above his glasses to see, putting his eyes partially in shadow. He wears a button-up shirt, the sleeves rolled up. Light pours through a window behind us, sitting near his student desk & coffee cup.

3
1
11
Now is your chance!
LMCache Lab
@lmcacheOct 22
What should we ask Dongjoo Seo about KV cache system deployment? ๐Ÿ’ฌ Dongjoo Seo of Samsung speaks at 4:30 PM today at the LMCache hands-on workshop: "What we should consider for KV Cache system deployment." Reply with one question, and we will bring a few into the room. The workshop starts at 1:30 PM Pacific at Samsung, 3655 N First St, San Jose. It is free, and you can still register: โฐ na2.hubs.ly/H08rNRd0
Side panel: technical session, Dongjoo Seo, Samsung, 4:30 PM, Thu 22 Oct, San Jose. Large question: What should we ask Dongjoo Seo about KV Cache system deployment? luma.com/cm7eip1b

ALT Side panel: technical session, Dongjoo Seo, Samsung, 4:30 PM, Thu 22 Oct, San Jose. Large question: What should we ask Dongjoo Seo about KV Cache system deployment? luma.com/cm7eip1b

30
Karsten Wade [email protected] @quaid.bsky.social retweeted
LMCache Lab
@lmcacheOct 21
Tomorrow at 1:30 PM, doors open at Samsung, 3655 N First St, San Jose. ๐Ÿ“ Bring a laptop; it is recommended for the hands-on part. Parking is available, and signs lead you to check-in at the event location. Refreshments are provided. Setup help starts at 1:30 PM, so arrive early if you want someone to check your environment. ๐Ÿ› ๏ธ The LMCache hands-on workshop runs until 5:30 PM Pacific. It is free, and registration is required. โฐ na2.hubs.ly/H08k60h0
Large orange 1, day to go. Tomorrow at Samsung, San Jose: doors 1:30 PM, laptop recommended, parking, refreshments, follow the signs to check-in. Thu 22 Oct, 3655 N First St. luma.com/cm7eip1b

ALT Large orange 1, day to go. Tomorrow at Samsung, San Jose: doors 1:30 PM, laptop recommended, parking, refreshments, follow the signs to check-in. Thu 22 Oct, 3655 N First St. luma.com/cm7eip1b

1
1
2
192
See y'all there!
LMCache Lab
@lmcacheOct 16
Open Source AI Week starts today in the Bay Area and runs to 25 October. ๐Ÿ“… If you come for PyTorch Conference at the San Jose Convention Center on 20 and 21 October, stay one more day. On Thursday 22 October, the LMCache hands-on workshop runs 1:30 to 5:30 PM Pacific at Samsung, 3655 N First St, San Jose. ๐Ÿ“ Four hours with a live LMCache environment, engineering sessions, and a reception. Free, registration required: na2.hubs.ly/H08k5yg0
Open Source AI Week starts today. Timeline: Fri 16 Oct, the week starts; Tue 20 to Wed 21 Oct, PyTorch Conference, San Jose Convention Center; Thu 22 Oct, LMCache workshop, Samsung, San Jose. luma.com/cm7eip1b

ALT Open Source AI Week starts today. Timeline: Fri 16 Oct, the week starts; Tue 20 to Wed 21 Oct, PyTorch Conference, San Jose Convention Center; Thu 22 Oct, LMCache workshop, Samsung, San Jose. luma.com/cm7eip1b

28
Karsten Wade [email protected] @quaid.bsky.social retweeted
LMCache Lab
@lmcacheOct 15
After the workshop on Thursday 22 October, the mini-lmcache test environment stays open for your own experiments. ๐Ÿ› ๏ธ So what would you test first? A long shared prompt? A document that many requests read again? Reply with one line. ๐Ÿ’ฌ The hands-on deep dive is part of a free afternoon, 1:30 to 5:30 PM Pacific, at Samsung, 3655 N First St, San Jose. Registration is required: na2.hubs.ly/H08k5xM0
The test environment stays open after the session. Large question: What would you test first? Thu 22 Oct, 1:30 to 5:30 PM, Samsung, San Jose. luma.com/cm7eip1b

ALT The test environment stays open after the session. Large question: What would you test first? Thu 22 Oct, 1:30 to 5:30 PM, Samsung, San Jose. luma.com/cm7eip1b

1
1
1
129
My #Enterprise friends, we have a bouncing new #KVCache product! ๐Ÿ‘‡๐Ÿป Do you run your own inference using Open Weights models? Have you been managing KV cache natively at your inference engine layer? Tensormesh Platform works with all of that stuff & extends it into the future:
Tensormesh
@tensormeshOct 14
Today weโ€™ve announced to the world that ๐“๐ž๐ง๐ฌ๐จ๐ซ๐ฆ๐ž๐ฌ๐ก ๐๐ฅ๐š๐ญ๐Ÿ๐จ๐ซ๐ฆ, the ๐ฆ๐š๐ง๐š๐ ๐ž๐ฆ๐ž๐ง๐ญ ๐ฅ๐š๐ฒ๐ž๐ซ ๐Ÿ๐จ๐ซ ๐€๐ˆ ๐ข๐ง๐Ÿ๐ž๐ซ๐ž๐ง๐œ๐ž ๐๐š๐ญ๐š, is officially live and enterprise-ready ๐Ÿš€ Read the full announcement ๐Ÿ‘‡ na2.hubs.ly/H08nsMN0
1
1
52
Karsten Wade [email protected] @quaid.bsky.social retweeted
LMCache Lab
@lmcacheOct 13
CVE-2026-105192 (CVSS 3.1 score 9.8): remote code execution in LMCache multiprocess (MP) mode. The fix is merged into the dev branch and will ship in 0.5.6, expected this week. Affected: 0.3.9 through 0.5.5, the 0.5.6 release candidates, and dev branches before the fix. You are exposed if the ZeroMQ transport (port 5555 by default) binds a routable address, or if you started from our example Kubernetes deployment. Before you upgrade: move workers and servers to 0.5.6 together. The wire format has changed. Interim steps and compromise checks are in the update. Thanks to Yuval Moravchick of JFrog Security Research. blog.lmcache.ai/en/2026/10/1โ€ฆ

An Update on CVE-2026-105192

Device IPC deserialization fix merged into the dev branch On October 7, 2026, JFrog Security Research publicly disclosed a deserialization remote code execution vulnerability in LMCacheโ€™s mulโ€ฆ

blog.lmcache.ai
1
183
Karsten Wade [email protected] @quaid.bsky.social retweeted
LMCache Lab
@lmcacheOct 13
If you could ask the LMCache maintainers for one thing, what would it be? ๐Ÿ’ฌ A feature, a fix, a docs page, or a config example. Leave it in the replies. It is also a question on the registration form for our hands-on workshop, where you can ask in person: Thursday 22 October, 1:30 to 5:30 PM Pacific, at Samsung, 3655 N First St, San Jose. Free. ๐Ÿค na2.hubs.ly/H08k5mp0
Light card with orange quote marks. From the registration form: If you could ask the maintainers for one thing, what would it be? Thu 22 Oct, 1:30 to 5:30 PM, Samsung, San Jose. luma.com/cm7eip1b

ALT Light card with orange quote marks. From the registration form: If you could ask the maintainers for one thing, what would it be? Thu 22 Oct, 1:30 to 5:30 PM, Samsung, San Jose. luma.com/cm7eip1b

1
2
236
Today I learned: Where a facial wash product for women "gently cleanses and moisturizes ..." A face wash for men "cleans thoroughly and fights dryness ..." ๐Ÿซฏ๐Ÿšฑ
41
Karsten Wade [email protected] @quaid.bsky.social retweeted
Tensormesh
@tensormeshOct 1
Day 1 of The AI Conference SF is in the books! ๐ŸŽ‰ Come say hi to the team at Booth #214. We're excited to show how Tensormesh Platform can speed up AI inference and cut GPU costs with intelligent KV caching. See you on Day 2! #TheAIConference #AIInfrastructure #LLMInference #KVCache
1
4
8
193
If you are at this event, drop by and say howdy. I'll be representing @lmcache and chilling at the Tensormesh booth. Come ask your questions and tell us your thoughts on this new AI-native data layer.
Tensormesh
@tensormeshSep 29
SEE YOU THERE! We're at Booth #214 at T๐™๐™๐™š ๐˜ผ๐™„ ๐˜พ๐™ค๐™ฃ๐™›๐™š๐™ง๐™š๐™ฃ๐™˜๐™š 2026, Sept 30 to Oct 1 at Pier 48 in San Francisco. Come talk KV cache, GPU memory pressure, or anything else in your inference stack. See you there.
1
1
58
Karsten Wade [email protected] @quaid.bsky.social retweeted
LMCache Lab
@lmcacheSep 28
What is a meetupโ€ขworkshop? Well, at this one it means a live LMCache environment is stood up before you and made ready for your own experiments. That is the plan for our hands-on meetupโ€ขworkshop in San Jose on Tuesday 6 October. You move from listening to testing: you explore live deployments, test your understanding of LMCache in the environment, and talk directly with experts and peers. ๐Ÿ› ๏ธ A laptop is recommended for the hands-on part. โฐ 1:30 to 5:30 PM Pacific time, at Samsung, 3655 N First St. Free, registration required. luma.com/cm7eip1b
Four hours, hands-on. Work against a live LMCache test environment; laptop recommended. Illustrated terminal with a sample request. Tue 6 Oct, 1:30 to 5:30 PM, Samsung, San Jose. luma.com/cm7eip1b

ALT Four hours, hands-on. Work against a live LMCache test environment; laptop recommended. Illustrated terminal with a sample request. Tue 6 Oct, 1:30 to 5:30 PM, Samsung, San Jose. luma.com/cm7eip1b

1
1
3
183
Karsten Wade [email protected] @quaid.bsky.social retweeted
LMCache Lab
@lmcacheSep 27
What changes in LLM serving when you keep the KV cache? As the PyPI summary makes clear, LMcache is "An LLM serving engine extension to reduce TTFT and increase throughput, especially under long-context scenarios." TTFT is time-to-first-token. ๐Ÿง  In San Jose on Tuesday 6 October, you can watch the same workload run with and without LMCache, and judge the difference yourself. No local install is planned. Free hands-on workshop, 1:30 to 5:30 PM Pacific time. Registration is required. โฐ luma.com/cm7eip1b
3
1
11
489
Karsten Wade [email protected] @quaid.bsky.social retweeted
LMCache Lab
@lmcacheSep 27
One question from our workshop registration form, for anyone who runs LLM inference: What would stop you from putting LMCache into production next month? One sentence is enough. If you are new to LMCache, tell us what you would need to know first. ๐Ÿ’ฌ Reply here. The same question is on the form for our free, hands-on LMCache workshop in San Jose on Tuesday 6 October, 1:30 to 5:30 PM Pacific time. ๐ŸŽŸ๏ธ Registration is required: luma.com/cm7eip1b
Dark LMCache card, from the registration form: What would stop you putting LMCache into production next month? Tue 6 Oct, 1:30 to 5:30 PM, Samsung, San Jose. luma.com/cm7eip1b

ALT Dark LMCache card, from the registration form: What would stop you putting LMCache into production next month? Tue 6 Oct, 1:30 to 5:30 PM, Samsung, San Jose. luma.com/cm7eip1b

1
167
Karsten Wade [email protected] @quaid.bsky.social retweeted
LMCache Lab
@lmcacheSep 27
Which inference engine do you use, and what kind of workloads do you run? Tell us in one line each. ๐Ÿ’ฌ Brevity is our friend, and fewer details is easier to parse: the engine on the first line, the workloads on the second. We ask the same two questions on the registration form for our free, hands-on LMCache workshop in San Jose. It is on Tuesday 6 October, 1:30 to 5:30 PM Pacific time, at Samsung, 3655 N First St. Registration is required. ๐Ÿ› ๏ธ luma.com/cm7eip1b
Light LMCache card: Which inference engine and which workload do you run? Blank lines to fill in for engine and workload. Tue 6 Oct, 1:30 to 5:30 PM, Samsung, San Jose. luma.com/cm7eip1b

ALT Light LMCache card: Which inference engine and which workload do you run? Blank lines to fill in for engine and workload. Tue 6 Oct, 1:30 to 5:30 PM, Samsung, San Jose. luma.com/cm7eip1b

1
1
3
323
๐Ÿง ๐Ÿคฏ ๐Ÿ˜‰
LMCache Lab
@lmcacheSep 25
The lmcache package on PyPI has passed 1,000,000 all-time downloads, per pepy.tech (CI traffic included). It stood at 1,002,795 on 2026-09-24. LMCache is an LLM serving engine extension that reduces time-to-first-token (TTFT) and increases throughput, especially in long-context scenarios. Current release: 0.5.5. Right now LMCache is a popular way to save money and reduce resource use for GPUs. If this doesn't matter to you directly, it probably matters to your customers. On GitHub, the project has 350+ contributors and about 11.9k stars. Thank you to everyone who has sent a pull request, reported an issue, or reviewed code. โญ github.com/LMCache/LMCache
pepy.tech chart of daily lmcache downloads on PyPI, June 25 to September 23, 2026, mostly 1,000 to 4,000 a day with a peak near 7,500 in mid-August. Totals: 1.0 million all-time, 65.3 thousand in the last 30 days.

ALT pepy.tech chart of daily lmcache downloads on PyPI, June 25 to September 23, 2026, mostly 1,000 to 4,000 a day with a peak near 7,500 in mid-August. Totals: 1.0 million all-time, 65.3 thousand in the last 30 days.

2
53
Concretely, this tweet is load-bearing.
1
33
And there we have it, a brand-new bouncing baby product, downstream and enterprise-ready!
Tensormesh
@tensormeshSep 14
๐˜๐จ๐ฎ๐ซ ๐ข๐ง๐Ÿ๐ž๐ซ๐ž๐ง๐œ๐ž ๐ฌ๐ญ๐š๐œ๐ค ๐ก๐š๐ฌ ๐š๐ฆ๐ง๐ž๐ฌ๐ข๐š. Before a model can answer, it has to read your prompt, and that reading is most of the GPU work in the request. Almost every setup throws the result away the moment it sends the response, so the next request reads it all over again. Same system prompt, same retrieved documents, same conversation history. That discarded work is the KV cache. Today we're launching ๐“๐ž๐ง๐ฌ๐จ๐ซ๐ฆ๐ž๐ฌ๐ก ๐๐ฅ๐š๐ญ๐Ÿ๐จ๐ซ๐ฆ, a KV cache that remembers. It tiers cached context across GPU memory, host RAM, and storage you already run, so when memory fills up or a pod restarts, state moves down a tier instead of vanishing. ย  From the team behind @LMCache, the open-source KV caching engine, now past 10,000 stars on GitHub. ย Runs on your own GPUs, in your own environment. Tensormesh Platform serves vLLM on Kubernetes, with more engines and storage backends on the way. Full write-up on the ๐›๐ฅ๐จ๐ :๐Ÿ‘‡ na2.hubs.ly/H07PyVf0
74
Saturday's Bits & Bobs from Distro of the Week features Linux news from the past week. Enjoy! distrooftheweek.com/2026/09/โ€ฆ

Bits & Bobs: KDE Plasma ready to test

Compiled by Larry Cafiero The KDE Plasma beat goes on . . . Marcus Nestor at 9 to 5 Linux reports on Thursday that the KDE Plasma 6.8 desktop environment is ready for public beta testing, and a secโ€ฆ

distrooftheweek.com
1
1
2
95
Karsten Wade [email protected] @quaid.bsky.social retweeted
Tensormesh
@tensormeshAug 18
It's 3am on a holiday weekend. GPUs look healthy. Benchmarks say you're fine. Latency is climbing anyway. We talked to Qian Cao, Founding Engineer @Tensormesh, about why benchmarks don't predict production AI performance โ€” and what actually breaks at hyperscale. tensormesh.ai/blog-posts/buiโ€ฆ
1
3
123
Karsten Wade [email protected] @quaid.bsky.social retweeted
LMCache Lab
@lmcacheAug 6
๐Ÿš€ ๐—Ÿ๐— ๐—–๐—ฎ๐—ฐ๐—ต๐—ฒ ๐˜ƒ๐Ÿฌ.๐Ÿฑ.๐Ÿฏ ๐—ถ๐˜€ ๐—ผ๐˜‚๐˜! โœจ New model support โ€ข Kimi K3 (day-0, incl. MLA-layer KV shapes) โ€ข MiniMax M3 and other Mamba models fixed for vLLM 0.26 ๐Ÿ—‚๏ธ Fleet-wide cache directory (MP mode) โ€ข MP servers stream cache events into a shared key + token directory, with a query API, quota accounting, and global L1 token matching for CacheBlend ๐Ÿ”ง Highlights โ€ข Hot-plug Device-DAX L1 devices at runtime โ€” no restart โ€” plus batched DAX L2 loads โ€ข Faster CacheBlend retrieve: native plan executor with kernel fusion, new ๐™ฝ๐™ป_๐š‡_๐™ฝ๐™ฑ_๐™ฑ๐š‚๐š…_๐™ฑ๐š‚๐š‚ layout โ€ข AES-GCM encryption for KV cache at rest, configurable from the operator โ€ข Multimodal support in MP mode (no encoder cache yet) and non-blocking ๐šœ๐š๐š˜๐š›๐šŽ_๐š”๐šŸ_๐šŠ๐šœ๐šข๐š—๐šŒ for SGLang โ€ข Prebuilt ROCm wheels (gfx942/gfx950) and NVMe FDP placement for RawBlock ๐—ง๐—ต๐—ฎ๐—ป๐—ธ๐˜€ ๐˜๐—ผ ๐—ผ๐˜‚๐—ฟ ๐Ÿญ๐Ÿฑ ๐—ป๐—ฒ๐˜„ ๐—ฐ๐—ผ๐—ป๐˜๐—ฟ๐—ถ๐—ฏ๐˜‚๐˜๐—ผ๐—ฟ๐˜€! ๐Ÿ™Œ Full changelog: github.com/LMCache/LMCache/cโ€ฆ #LMCache #LLMInference #OpenSource #KVCache #ArtificialIntelligence
๐Ÿค– Made with AI
4
11
493
Load more