The Ledger
Every statement that passed quotation and attribution checks. Mix any filter with any other: certainty 1/5, debate potential 5/5, or both at once.
why aren't all 10 resolved? a statement only gets an assessment when the public record can support or contradict it. opinions and what-ifs never can, and 0 checkable ones are still open, waiting for their date. predictions held up or didn't; assertions are supported or contradicted. on every card: ▮▮▮▮▮ certainty · ▮▮▮▮▮ debate potential. speakers are clickable
Lattner calls vLLM a 'hot mess' due to too many stakeholders
“VLM seems much more like a massive community with a lot of stakeholders, a lot of stuff going on, and it's kind of a hot mess.”
Lattner: Modular MAX is 'more open source' than vLLM
“This thing's more open source than VLM because VLM depends on all these crazy binary CUDA kernels and stuff like this that are just opaque blobs from NVIDIA, right?”
Varun Mohan: Codeium would have failed if it used vLLM
“If we use VLLM, we would not be talking with you right now.”
Mohan: Codeium would not have survived if it relied on vLLM
“If we use VLLM, we would not be talking with you right now.”
Zhang: SGLang outperforms vLLM and has better usability than TensorRT-LLM
“I think for the common use case, maybe not, not the DeepSeq VIII, for the common use case, I think SGLAN's performance is better than FLM, and its usability is better than TensorFlow TLM.”
Morris: vLLM and SGLang are here to stay and will grow more complex
“I also think, ah, VLLM and SGLang seem, like, really good and important and here to stay. Like, they'll probably just get larger and more complex to accommodate future systems”
Zhang: vLLM does not support DeepSeek MLA while SGLang does
“Something like DeepSeq V-II, they proposed attention parent named MLA, multi-latent attention, and I think SGLAN is the only framework to support that. Maybe LightLM and TRTM also support, but VLM doesn't support.”
Zhang: SGLang achieves higher cache hit rates using block size of one
“Redix cache, I think it's the technology of the prefix caching, and it is a special case for something like block size is one, you know, for VLM or for other frameworks, they use something block size, 32, and SGLAN use the block size one. I think if you use th…”
Jamil: Chunked prefill is experimental in vLLM, likely used by majors
“This is called the chunked pre-fill, and it's an experimental feature that has been recently introduced in VLLN, but it's probably used in more sophisticated inference engines at major companies.”
Ermon: Inception Labs built proprietary engine for production inference traffic
“So just like you would normally serve an LLM using a VLLM or SGLang or a Tensor or TLLM, we have built our own inference engine. And so we are supporting production traffic already with our own inference engine. We support continuous batch and quantization.”