new | show | ask | jobs Github

binyu 4 hours ago

> Now at 40-50tok/s generation and ~2000 tok/s

Not clear how you went from ~11-14 to ~40-50 tok/s. Is it by running the quant native model and adding a second Spark?

Cheers

▲

ttsiodras 2 hours ago | parent | next [-]

Just chiming in - the claims above are real, I have very similar numbers in a cluster of 2x GX10 I have access to.

Instructions to reproduce, and benchmarks here: https://forums.developer.nvidia.com/t/deepseek-v4-flash-offi...

▲

wolttam 4 hours ago | parent | prev [-]

I suspect DwarfStar could probably squeeze more performance out of the single spark, maybe up closer to 20tok/s.

Moving to 2 sparks meant switching to vLLM with 2-way tensor parallelism and working multi-token prediction. The parallelism and MTP on top of better tuned kernels[1] gave an extremely nice boost! I was quite pleased. I've seen bursts up to 60tok/s at ~150k context - sometimes the MTP seems to really kick in (i.e. high acceptance rate on its tokens)

Currently running a custom vLLM build put together by some folks on the Nvidia forums[2], which speaks to how early support for the model is.

[1]: https://github.com/lukealonso/b12x

[2]: https://forums.developer.nvidia.com/t/372268

▲

binyu 4 hours ago | parent | next [-]

Personally, I've tried to squeeze more tok/s for a single DGX Spark deployment and DeepSeek V4 Flash but only got marginal improvements. There's work to do on fusing kernels and other optimizations that are already on antirez's roadmap so it is not worth duplicating efforts.

I've had positive experiences running GLM 4.7 via vLLM, tool calling works well and the inference is fast. Do you run DeepSeek V4 Flash on vLLM?

	▲	wolttam 4 hours ago \| parent [-]
		Yep, those are the numbers I'm getting with DSv4 Flash on vLLM across 2 sparks.

▲

doctorpangloss an hour ago | parent | prev [-]

DeepSeek v4 Flash MTP is a training optimization. It doesn't make inference run faster, it must run the entire model forward as the "verifier." This is in the paper, and this is why the docs they release do not mention using it for accelerated inference.

Eventually, I'm going to stop writing stuff like this @dang, because even though it is literally being read by a human, it's going to just be copy and pasted into a chatbot, which will actually spend the time trying to comprehend what I am saying.

	▲	wolttam 20 minutes ago \| parent [-]
		> MTP in Inference. Our MTP strategy mainly aims to improve the performance of the main model, so during inference, we can directly discard the MTP modules and the main model can function independently and normally. Additionally, we can also repurpose these MTP modules for speculative decoding to further improve the generation latency.[1] (emphasis mine) > Instead of predicting just the next single token, DeepSeek-V3 predicts the next 2 tokens through the MTP technique. Combined with the framework of speculative decoding (Leviathan et al., 2023; Xia et al., 2023), it can significantly accelerate the decoding speed of the model.[2] > As DeepSeek-V3, DeepSeek-V4 series also set MTP modules and objectives. Given that the MTP strategy has been validated in DeepSeek-V3, we adopt the same strategy for DeepSeek-V4 series without modification.[3] [1]: https://arxiv.org/pdf/2412.19437#subsection.2.2 [2]: https://arxiv.org/pdf/2412.19437#subsubsection.5.4.3 [3]: https://arxiv.org/pdf/2606.19348v1#subsection.2.1 Side comment: I feel you may be too cynical towards your fellow commenters.