Fixing "theoretical" nondeterminism for a totally closed individual input-output pair doesn't solve the two "practical" nondeterminism problems, where the exact same input gives different results given different preceding context, and where a slightly transformed input doesn't give a correctly transformed result.
Until those are addressed, closed-system nondeterminism doesn't really help except in cases where a lookup table would do just as well. You can't use "correct" unit tests or evaluation sets to prove anything about inputs you haven't tested.
There is no such thing as "exactly the same input, but with different preceding context". The preceding context is input!
If you were to obtain exactly the same output for a given input prompt, regardless of context, then that would mean that the context is being ignored, which is indistinguishable from the session not maintaining any context such that each prompt is in a brand new empty context.
Now what some people want is requirements like:
- The different wording of a prompt with exactly the same meaning should not change anything in the output; e.g. whether you say "What is the capital of France" or "What is France's capital" the answer should be verbatim identical.
- Prior context should not change responses in ways that don't have any interaction with the context. For instance, a prompt is given "what is 2 + 2", then the answer should always be the same, except if the context instructs the LLM that 2 + 2 is to be five.
These kinds of requirements betray a misunderstanding of what these LLMs are.
It's going to backfire. In real scenarios (not regression testing) users don't want to see the exact same thing twice out of the LLM in the same session in spite of trying to refine the result with more context.
There are going to be false positives: text that is subtly different from a previous response is misidentified as a duplicate such that the previous response is substituted for it, frustrating the user.
Not an expert, but I've been told RAG in combination with a database of facts is one way to get more consistency here. Using one of the previous examples, you might have a knowledge store (usually a vector database of some kind) that contains a mapping of countries to capitols and the LLM would query it whenever it had to come up with an answer rather than relying on whatever was baked into the base model.
> where the exact same input gives different results given different preceding context
Why and how is this a problem?
If 'preceding context' doesn't cause different results, it means you can simply discard the context. Why do I want that? It's not how I expect a tool to work (I expect vim responds differently to my input after I switch to the insert mode). It's absolutely not how I expect intelligence to work either. It sounds like the most extreme form of confirmation bias.
"in collaboration with others at Thinking Machines"
If you're old enough, you might remember Danny Hillis' Thinking Machines from the late 80s. I wish they had chosen a different name (I say this for nostalgic reasons, having been in front of one of those cubes glowing with red LEDs back in the late 80s at MIT's AI Lab" (renamed to CSAIL at some point). Feynman did some amazing work on that, too: https://longnow.org/ideas/richard-feynman-and-the-connection...
In the U.S., the “THINKING MACHINES” trademarks were owned by Thinking Machines Corporation (the company Hillis co-founded), not Hillis personally, and those registrations were cancelled in 1998–1999.
USPTO Report
+1
The company itself went bankrupt in 1994 and its assets were dispersed (e.g., to Sun Microsystems, later Oracle).
There’s a new, pending USPTO application for “THINKING MACHINES” filed in 2025 by Thinking Machines Lab Inc., the company founded by Amira Murati.
Sometimes, the reason for non-determinism is implementation-specific. For instance, in GPT-2's source code (I haven't checked other model versions), setting the temperature in the GUI does not lead to a value of 0 but "epsilon" (a very small value larger than 0), to avoid a division by zero error in the code, which makes sense.
For many applications, non-determinism implies "useless".
This has been a long standing issue with LDA topic models. In particular in the legal, financial and regulatory domains, if a method is not deterministic, it may be illegal to use it or it may lead to follow-on requirements that one does not want (e.g. all screens shown to humans must be preserved to be able to go back and reconstruct what exactly happened to a particular user in a particular second).
Natural language is ambiguous. It needs to be. I think the approach here of trying to figure out how to make circles into squares, and argue why circles should be squares, is misguided.
Discussions of this type are going to eventually morph into better understanding of how to accept ambiguity and randomness in language, and further shape it with other larger sub-patterns beyond the little proto-grammars that the QKV projection matrices extract.
“Language ambiguity with determinism”? Sure I can juxtapose the terms but if it’s semantically inconsistent, then what we mean by that is not a deterministic, definitive thing. You’re chasing your tail on this ‘goal’.
Ambiguity: The request/prompt leaves a lot of room for interpretation. Many qualitatively different answers may be correct, relative to the prompt. Different or non-deterministic models will return highly variance results.
Determinism: If a model is given the exact same request/prompt twice, its two responses will also be identical. Whether or not the consistent response qualifies as correct.
The two concepts are very different.
(Ambiguous vs. precise prompt) x (Deterministic vs. Non-deterministic model) = 4 different scenarios.
A model itself can be non-deterministic without being ambiguous. If you know exactly how it functions, why it is non-deterministic (batch sensitive for instance), that is not an ambiguous model. Its operation is completely characterized. But it is non-deterministic.
An ambiguous model would simply be model whose operation was not characterized. A black box model for instance. A black box model can be deterministic and yet ambiguous.
Are you talking about the “Thinking Machines” company that shut down in 1994? Took me some digging to figure it out, doesn’t seem well-known enough to be the reason - it’s just a nice (and relatively obvious) name.
Yes. Danny Hillis’ Thinking Machines Corporation, an AI company which created its own massive parallel processing supercomputer hardware.
“We are building a machine that will be proud of us” was their corporate motto. And that was in 1983.
One of those Machines is on view at the Computer History Museum in Mountain View.
Back then, they could be ordered in “Darth Vader Black”, no kidding here. You can also see a couple of them (the CM-5) as the stereotypical supercomputer in the original Jurassic Park.
It may not be a household name like Apple or Microsoft but its flagship product the Connection Machine is somewhat iconic in (super)computing history. The physical design of the machine is cool and unforgettable looking, plus recurring HN favorite Richard Feynman contributed to the original architecture.
I love high quality blog post style research discussion - Anthropic has been leading the charge with this recently and it's great to see it spreading. OpenAI was also doing this during all the RL research days.
I really hope we will get deterministic LLMs in the future. Even if it causes slightly slower response times.
Nondeterminism is what currently keeps me from working with other developers.
As I wrote in "Prompt Coding" [1], these days I am not looking for good code. I am looking for prompts that create good code. But how do you share prompts among developers when they produce different code every time? You cannot simply state "Here, I found a prompt that makes gpt-5-2025-08-07 output a solution with all the desired attributes".
Similar with images. At the moment, for most image models, you cannot outsource the task of writing prompts that create the desired images. Because most image models will not create the same image when given the same prompt and parameters.
Surely if you end up relying on a given prompt to produce the exact same code every time you should instead just check that code into source control the first time you generate it?
A deterministic LLM isn't going to behave appreciably differently from a non deterministic one if your input or context varies by even a tiny bit (pun intended) each time.
If nothing has changed, caching the result would certainly be cheaper. But if you're doing that as part of a test, it's not really running the test and it might defeat the purpose of the test.
i tried to create a makefile driven workflow based on this idea and ended up with https://github.com/khimaros/enc -- it suffers from the issues you raised
i'm hoping that it becomes more useful as models improve and become more reliable at producing working code (though determinism would be great for improving prompts).
For fun over the last few days, I've built a compressor / decompressor that uses the logits from an LLM, for each token in the input, then takes the ranks and exponential goolomb encodes them. Then you work in reverse to regenerate the original
It took me ages to get the prediction for the second token after "hello" to match the same as the prediction for the second token when running the model on the string "hello world", despite the fact that I was using a causal model. I tried all kinds of things before discovering that `quantized: false` was the important setting.
What's the Weissman score? Or more seriously :) did it perform well. Sounds like it should. If more and more text is AI slop it should do well.
I dont fully understand what you said but I guess higher probability logits are encoded with fewer bits. If your text is the LLM output then you may need a bit or two per token?
I used exponential golomb coding, so the rank 0 logit is encoded with a single bit, ranks 1 and 2 are encoded with three bits, ranks 3-6 are encoded with 5 bits, etc.
In terms of performance, I've not done any serious testing, but e.g. the wikipedia article on volcanos compresses to about 20% using GPT2. I've seen other strings compress even further.
The big issue is that while encoding is not unreasonable, decoding any significant amount of data is incredibly slow, since I'm doing a model run for every token in the output. It's bad enough that the scheme is probably unworkable as it is. I'm thinking about changing my code so that it streams out the tokens as it decodes them, so you're not just left there waiting for ages.
Very impressive! I guess this still wouldn't affect their original example
> For example, you might observe that asking ChatGPT the same question multiple times provides different results.
even with 0.0 temperature due to MOE models routing at a batch level, and you're very unlikely to get a deterministic batch.
> Not because we’re somehow leaking information across batches — instead, it’s because our forward pass lacks “batch invariance”, causing our request’s output to depend on the batch size of our forward pass.
The router also leaks batch-level information across sequences.
> even with 0.0 temperature due to MOE models routing at a batch level, and you're very unlikely to get a deterministic batch.
I don’t think this is correct - MoE routing happens at per token basis. It can be non deterministic and batch related if you try to balance out your experts load in a batch but that’s performance optimization (just like all of the blogpost) and not the way models are trained to work.
I think this means that the results might also be non-deterministic across hardware revisions b/c I don't think they verified that the kernels will work the same on different GPU & TPU versions b/c how do they know that the compiler will not re-order the operations behind their back?
Yes, there’s usually no guarantee on how different hardware does operations (for example, even if the hardware is correctly rounding intermediate results, different hardware may use different tile sizes). The reproducibility here is for runs on the same machine.
Compilers can also reorder operations but in practice this is rarely an issue because kernels typically synchronize frequently and this limits the ability for compilers to reorder things. This isn’t to say it doesn’t happen, but even if it does happen it’s likely because the compiler changed because the code they generate is generally run-to-run identical.
You can prevent reordering with sufficient amounts of compiler abuse.
With revisions, you're trying to ensure a consistent floating point environment where the operations used are deterministic, and used in the same order with the same inputs. The best way to do that is to use operations that adhere to a mostly deterministic standard like IEEE-754.
Ensuring the same floating-point algorithm workload behaves exactly the same on two distinct workstations is a heck of a lot of work that almost no one is willing to pay for.
Not only that but heterogeneous clusters (inevitable at a large enough scale) will also have non-deterministic outputs. So it's great that they wrote kernels to make the forward pass deterministic but getting rid of it entirely at data center scale would mean that they'd also have to do this type of work across cluster nodes as well to maintain "cluster" invariance & not just batch invariance.
As the bottom of LLM inference, it is sampling for the next token based on the probability distribution conditioned on the tokens currently in the context window. If the distribution exhibits degeneracy in probability for more than token, outcome of the sampling will naturally, as it should, be nondeterministic. It should be left alone.
Where this gets really complicated is when you are chaining many LLM calls together (basically any agent). A slight deviation in the call stack can throw off everything else.
A = torch.randn(2048, 2048, device='cuda', dtype=torch.bfloat16)
B = torch.randn(2048, 2048, device='cuda', dtype=torch.bfloat16)
ref = torch.mm(A, B)
for _ in range(1000):
assert (torch.mm(A, B) - ref).abs().max().item() == 0
I’m sort of surprised that Torch doesn’t have some kind of lazy evaluation thing to avoid computing anything here. I thought that was one of the nice things about all these fancy frameworks (if I wanted the computer to actually do silly things when I asked it to, I would use BLAS directly, right?).
Maybe I'm missing something, but in this case, wouldn't being lazy would be pure overhead? I don't see anything can be lazy here. The reference computed once, nanoseconds before it's needed, and test cases computed at the time of comparison, then tossed away.
What would hope to be achieved by making this case lazy? If you wanted these to run in parallel, with a multi-gpu system, you would use the appropriate parallel interface.
I don't understand. Since it's not using the parallel interface, only one operation can happen at a time. This would be, literally, sequential execution with extra overhead, in this case. Again, in this case, what would hope to be achieved from doing things lazily, since the lazy operations would immediately be followed by their evaluation?
The parallel interface, which is async, is probably what you're lookin for.
The Python commands are encountered sequentially. One could image a library where the Python commands build the computation under the hood. Then, the library would be able to take advantage of situations like this one (or, more practically, reorder multiplications and/or avoid unnecessary temporaries).
"I had no problem getting deterministic LLM outputs when I experimented with this 6 months ago" looks like you're using llama-cpp in that repo. This is about vllm serving many requests at once, at long sequence lengths.
> As it turns out, our request’s output does depend on the parallel user requests. Not because we’re somehow leaking information across batches — instead, it’s because our forward pass lacks “batch invariance”, causing our request’s output to depend on the batch size of our forward pass.
Seed your PRNGs and call torch.use_deterministic_algorithms(True) to get the deterministic kernels. They may be slightly slower, but in practice, you probably will not notice.
Note that results will still differ between different drivers and GPUs. It would be great if NVIDIA tried harder in that regard.
The blog post is about LLM non-determinism in the context of serving at scale (variable batch size). The page you link is only about run-to-run determinism implicitly assuming a fixed batch size.
His solution still relies on greedy (temperature 0) sampling, which is probably not optimal for model performance on various tasks. For example, Gemini 2.5 uses temperature 1 by default. But deterministic inference with temperature >0 can still be achieved by using pseudorandom sampling with a fixed seed.
Conceptually setting temperature to be >0 doesn't actually introduce any non-determinism. If your sampler is seeded then it will always choose the same next token. Higher temperature only flattens the logit distribution.
The point of the blog is that even at "supposed" deterministic generative sampling, non-determinism creeps in. This in turn has disastrous effects in very real experiments.
cool project but if this is what you are producing with $2 billion funding, i doubt you will survive. This is the type of article a grad student would write over a weekend.
Who needs a working product when you can spend all day designing the most WEWORK looking website and slap some pseud slop on it. It's like crypto "startups" but it's not even fun.
I am baffled that I still run against these statement years after LLM's have been around. LLM's are deterministic and always have been. The reason people are having issues with them is because they are basing their assumptions on api based experiments. Like my man, how can you be making these statements when you haven't done the due diligence of running the LLM on your own hardware with all of the variables locked down and accounted for? If you do just that it would become obviously clear that they are deterministic and most of the time the reason you see the non deterministic behavior is because you have not controlled for a variable. Usually prompt caching, batch processing or some other obvious variable. Now this is related to within same system deterministic behavior. You might get different answers when running on a different gpu, but at least for same systems the behavior is 100% identical if you account for all server startup flags and properly account for things like prompt cashing, slot contamination etc...
I suggest you look up the name of the main author of TFA before assuming they don’t know what they are talking about.
This is literally one of the most knowledgeable person on the topic. I think you are the one that hasn’t peeled enough layers to connect with what they are saying.
Hold on a second. A transformer produces deterministically a probability distribution over the token alphabet from the context. Then one samples from this distribution. This is random and meant to be random.
The sampling process isn't random. If you sample with identical sampling parameters and identical values for said parameters, you will always get same results. You only start getting "non deterministic" behavior when you start using more complex systems outside the scope of your control like multi gpu systems and batch processing. One llm sampled with cash prompting off and and batch processing off will always generate same results if all values are same.
It's possible to deterministically sample from a probability distribution. For example, just seed your RNG with a constant, or with the SHA256 hash of the context.
Well yes, you can "hack" the pseudorandom number generator, but... that's not really the point when talking about determinism in LLMs is it? I mean the mathematical idea of the standard LLM is certainly truly random.
I suppose I have issues with the way "determinism" is used in the title of this article. It can mean different things to different people and in my mind stating that "Defeating Nondeterminism in LLM Inference" frames it as an actual issue with LLM inference. But its not, its an issue with LLM inference when you start using large scale inference with more complex parts such as systems which use multi gpu inference systems or batching processes and other mechanisms. It is not an issue when using an LLM without those more complex parts. Stating it this way muddies the signal and gives a false sense that this is a fundamental issue with architecture, where its an issue of the systems at scale...
Fixing "theoretical" nondeterminism for a totally closed individual input-output pair doesn't solve the two "practical" nondeterminism problems, where the exact same input gives different results given different preceding context, and where a slightly transformed input doesn't give a correctly transformed result.
Until those are addressed, closed-system nondeterminism doesn't really help except in cases where a lookup table would do just as well. You can't use "correct" unit tests or evaluation sets to prove anything about inputs you haven't tested.
There is no such thing as "exactly the same input, but with different preceding context". The preceding context is input!
If you were to obtain exactly the same output for a given input prompt, regardless of context, then that would mean that the context is being ignored, which is indistinguishable from the session not maintaining any context such that each prompt is in a brand new empty context.
Now what some people want is requirements like:
- The different wording of a prompt with exactly the same meaning should not change anything in the output; e.g. whether you say "What is the capital of France" or "What is France's capital" the answer should be verbatim identical.
- Prior context should not change responses in ways that don't have any interaction with the context. For instance, a prompt is given "what is 2 + 2", then the answer should always be the same, except if the context instructs the LLM that 2 + 2 is to be five.
These kinds of requirements betray a misunderstanding of what these LLMs are.
I wonder if there's a way to use an LLM to rewrite the prompt, standardizing the wording when two prompts mean the same thing?
It's going to backfire. In real scenarios (not regression testing) users don't want to see the exact same thing twice out of the LLM in the same session in spite of trying to refine the result with more context.
There are going to be false positives: text that is subtly different from a previous response is misidentified as a duplicate such that the previous response is substituted for it, frustrating the user.
Google search rewrites misspelled search queries and also lets you override it if that's not what you want. Maybe something similar would work?
Not an expert, but I've been told RAG in combination with a database of facts is one way to get more consistency here. Using one of the previous examples, you might have a knowledge store (usually a vector database of some kind) that contains a mapping of countries to capitols and the LLM would query it whenever it had to come up with an answer rather than relying on whatever was baked into the base model.
Deterministically, you mean? ;)
> where the exact same input gives different results given different preceding context
Why and how is this a problem?
If 'preceding context' doesn't cause different results, it means you can simply discard the context. Why do I want that? It's not how I expect a tool to work (I expect vim responds differently to my input after I switch to the insert mode). It's absolutely not how I expect intelligence to work either. It sounds like the most extreme form of confirmation bias.
This is really useful in reproducing bugs.
I was with you until you said it “doesn’t really help”. Did you mean “doesn’t completely solve the problem “?
"in collaboration with others at Thinking Machines"
If you're old enough, you might remember Danny Hillis' Thinking Machines from the late 80s. I wish they had chosen a different name (I say this for nostalgic reasons, having been in front of one of those cubes glowing with red LEDs back in the late 80s at MIT's AI Lab" (renamed to CSAIL at some point). Feynman did some amazing work on that, too: https://longnow.org/ideas/richard-feynman-and-the-connection...
In the U.S., the “THINKING MACHINES” trademarks were owned by Thinking Machines Corporation (the company Hillis co-founded), not Hillis personally, and those registrations were cancelled in 1998–1999. USPTO Report +1
The company itself went bankrupt in 1994 and its assets were dispersed (e.g., to Sun Microsystems, later Oracle).
There’s a new, pending USPTO application for “THINKING MACHINES” filed in 2025 by Thinking Machines Lab Inc., the company founded by Amira Murati.
I make this mistake every time I see their name.
I thought this was pretty well known (at least in the JAX/XLA world). I've hit this many times and got batch variance explained to me before: https://github.com/google-deepmind/penzai/issues/82 and https://github.com/jax-ml/jax/issues/20047#issuecomment-1975...
Sometimes, the reason for non-determinism is implementation-specific. For instance, in GPT-2's source code (I haven't checked other model versions), setting the temperature in the GUI does not lead to a value of 0 but "epsilon" (a very small value larger than 0), to avoid a division by zero error in the code, which makes sense.
For many applications, non-determinism implies "useless". This has been a long standing issue with LDA topic models. In particular in the legal, financial and regulatory domains, if a method is not deterministic, it may be illegal to use it or it may lead to follow-on requirements that one does not want (e.g. all screens shown to humans must be preserved to be able to go back and reconstruct what exactly happened to a particular user in a particular second).
Natural language is ambiguous. It needs to be. I think the approach here of trying to figure out how to make circles into squares, and argue why circles should be squares, is misguided.
Discussions of this type are going to eventually morph into better understanding of how to accept ambiguity and randomness in language, and further shape it with other larger sub-patterns beyond the little proto-grammars that the QKV projection matrices extract.
Yes, but determinism != ambiguity, because determinism means: for this exact input the same exact output needs to follow.
If I ask the same model the same question I should be able to deterministically get the same answer.
Now if we phrase the same question slightly differently we would expect to get a slightly different answer.
> Now if we phrase the same question slightly differently we would expect to get a slightly different answer.
You wouldn't get this from an LLM though, a tiny change in starting point gets a massive change in output, its a chaotic system.
Me: What’s an example of a dice roll?
LLM: 1
“Language ambiguity with determinism”? Sure I can juxtapose the terms but if it’s semantically inconsistent, then what we mean by that is not a deterministic, definitive thing. You’re chasing your tail on this ‘goal’.
Ambiguity: The request/prompt leaves a lot of room for interpretation. Many qualitatively different answers may be correct, relative to the prompt. Different or non-deterministic models will return highly variance results.
Determinism: If a model is given the exact same request/prompt twice, its two responses will also be identical. Whether or not the consistent response qualifies as correct.
The two concepts are very different.
(Ambiguous vs. precise prompt) x (Deterministic vs. Non-deterministic model) = 4 different scenarios.
A model itself can be non-deterministic without being ambiguous. If you know exactly how it functions, why it is non-deterministic (batch sensitive for instance), that is not an ambiguous model. Its operation is completely characterized. But it is non-deterministic.
An ambiguous model would simply be model whose operation was not characterized. A black box model for instance. A black box model can be deterministic and yet ambiguous.
> LLM: 1
A perfectly acceptable answer.
If it answers 1 every time it's still a perfectly acceptable answer.
If you really want that to work while being reproducible, maybe give it a random number tool and set the seed?
I am still irritated by the name of the company.
What is the reasoning behind these schemes? The hope that bits of the properties of legendary companies will rub off onto the new venture?
As if naming the next best venture PARC will inevitably create a breakthrough in networking just by the arrangement of four letters.
Are you talking about the “Thinking Machines” company that shut down in 1994? Took me some digging to figure it out, doesn’t seem well-known enough to be the reason - it’s just a nice (and relatively obvious) name.
Yes. Danny Hillis’ Thinking Machines Corporation, an AI company which created its own massive parallel processing supercomputer hardware.
“We are building a machine that will be proud of us” was their corporate motto. And that was in 1983.
One of those Machines is on view at the Computer History Museum in Mountain View. Back then, they could be ordered in “Darth Vader Black”, no kidding here. You can also see a couple of them (the CM-5) as the stereotypical supercomputer in the original Jurassic Park.
More here: https://en.m.wikipedia.org/wiki/Thinking_Machines_Corporatio...
And in the original Jurassic Park! https://www.google.com/search?q=jurassic+park+cm-5
[addendum: posted this too quickly & didn't see it in the comment above. duh.]
It may not be a household name like Apple or Microsoft but its flagship product the Connection Machine is somewhat iconic in (super)computing history. The physical design of the machine is cool and unforgettable looking, plus recurring HN favorite Richard Feynman contributed to the original architecture.
The thinking is free marketing and the same reason trademarks were invented
I love high quality blog post style research discussion - Anthropic has been leading the charge with this recently and it's great to see it spreading. OpenAI was also doing this during all the RL research days.
I really hope we will get deterministic LLMs in the future. Even if it causes slightly slower response times.
Nondeterminism is what currently keeps me from working with other developers.
As I wrote in "Prompt Coding" [1], these days I am not looking for good code. I am looking for prompts that create good code. But how do you share prompts among developers when they produce different code every time? You cannot simply state "Here, I found a prompt that makes gpt-5-2025-08-07 output a solution with all the desired attributes".
Similar with images. At the moment, for most image models, you cannot outsource the task of writing prompts that create the desired images. Because most image models will not create the same image when given the same prompt and parameters.
[1]: https://www.gibney.org/prompt_coding
Surely if you end up relying on a given prompt to produce the exact same code every time you should instead just check that code into source control the first time you generate it?
A deterministic LLM isn't going to behave appreciably differently from a non deterministic one if your input or context varies by even a tiny bit (pun intended) each time.
If nothing has changed, caching the result would certainly be cheaper. But if you're doing that as part of a test, it's not really running the test and it might defeat the purpose of the test.
i tried to create a makefile driven workflow based on this idea and ended up with https://github.com/khimaros/enc -- it suffers from the issues you raised
i'm hoping that it becomes more useful as models improve and become more reliable at producing working code (though determinism would be great for improving prompts).
For fun over the last few days, I've built a compressor / decompressor that uses the logits from an LLM, for each token in the input, then takes the ranks and exponential goolomb encodes them. Then you work in reverse to regenerate the original
It took me ages to get the prediction for the second token after "hello" to match the same as the prediction for the second token when running the model on the string "hello world", despite the fact that I was using a causal model. I tried all kinds of things before discovering that `quantized: false` was the important setting.
What's the Weissman score? Or more seriously :) did it perform well. Sounds like it should. If more and more text is AI slop it should do well.
I dont fully understand what you said but I guess higher probability logits are encoded with fewer bits. If your text is the LLM output then you may need a bit or two per token?
I used exponential golomb coding, so the rank 0 logit is encoded with a single bit, ranks 1 and 2 are encoded with three bits, ranks 3-6 are encoded with 5 bits, etc.
In terms of performance, I've not done any serious testing, but e.g. the wikipedia article on volcanos compresses to about 20% using GPT2. I've seen other strings compress even further.
The big issue is that while encoding is not unreasonable, decoding any significant amount of data is incredibly slow, since I'm doing a model run for every token in the output. It's bad enough that the scheme is probably unworkable as it is. I'm thinking about changing my code so that it streams out the tokens as it decodes them, so you're not just left there waiting for ages.
Super interesting. For those unaware, this is the company Mira Murati (OpenAI previous CTO) started
Very impressive! I guess this still wouldn't affect their original example
> For example, you might observe that asking ChatGPT the same question multiple times provides different results.
even with 0.0 temperature due to MOE models routing at a batch level, and you're very unlikely to get a deterministic batch.
> Not because we’re somehow leaking information across batches — instead, it’s because our forward pass lacks “batch invariance”, causing our request’s output to depend on the batch size of our forward pass.
The router also leaks batch-level information across sequences.
> even with 0.0 temperature due to MOE models routing at a batch level, and you're very unlikely to get a deterministic batch.
I don’t think this is correct - MoE routing happens at per token basis. It can be non deterministic and batch related if you try to balance out your experts load in a batch but that’s performance optimization (just like all of the blogpost) and not the way models are trained to work.
Ah interesting, good point. So I guess expert-choice routing leaks across the batch. Now I'm not sure.
I think this means that the results might also be non-deterministic across hardware revisions b/c I don't think they verified that the kernels will work the same on different GPU & TPU versions b/c how do they know that the compiler will not re-order the operations behind their back?
Yes, there’s usually no guarantee on how different hardware does operations (for example, even if the hardware is correctly rounding intermediate results, different hardware may use different tile sizes). The reproducibility here is for runs on the same machine.
Compilers can also reorder operations but in practice this is rarely an issue because kernels typically synchronize frequently and this limits the ability for compilers to reorder things. This isn’t to say it doesn’t happen, but even if it does happen it’s likely because the compiler changed because the code they generate is generally run-to-run identical.
You can prevent reordering with sufficient amounts of compiler abuse.
With revisions, you're trying to ensure a consistent floating point environment where the operations used are deterministic, and used in the same order with the same inputs. The best way to do that is to use operations that adhere to a mostly deterministic standard like IEEE-754.
> will not re-order the operations behind their back?
Valid point. Floating point summation is not always commutative.
Ensuring the same floating-point algorithm workload behaves exactly the same on two distinct workstations is a heck of a lot of work that almost no one is willing to pay for.
Not only that but heterogeneous clusters (inevitable at a large enough scale) will also have non-deterministic outputs. So it's great that they wrote kernels to make the forward pass deterministic but getting rid of it entirely at data center scale would mean that they'd also have to do this type of work across cluster nodes as well to maintain "cluster" invariance & not just batch invariance.
As the bottom of LLM inference, it is sampling for the next token based on the probability distribution conditioned on the tokens currently in the context window. If the distribution exhibits degeneracy in probability for more than token, outcome of the sampling will naturally, as it should, be nondeterministic. It should be left alone.
It reminded me of this wonderful talk by the late Joe Armstrong (Erlang's creator): https://www.youtube.com/watch?v=lKXe3HUG2l4
Great post.
Where this gets really complicated is when you are chaining many LLM calls together (basically any agent). A slight deviation in the call stack can throw off everything else.
From their code:
I’m sort of surprised that Torch doesn’t have some kind of lazy evaluation thing to avoid computing anything here. I thought that was one of the nice things about all these fancy frameworks (if I wanted the computer to actually do silly things when I asked it to, I would use BLAS directly, right?).Maybe I'm missing something, but in this case, wouldn't being lazy would be pure overhead? I don't see anything can be lazy here. The reference computed once, nanoseconds before it's needed, and test cases computed at the time of comparison, then tossed away.
What would hope to be achieved by making this case lazy? If you wanted these to run in parallel, with a multi-gpu system, you would use the appropriate parallel interface.
I mean if you wait long enough, it is asking for
of something that can be identified as definitionally zero.I don't understand. Since it's not using the parallel interface, only one operation can happen at a time. This would be, literally, sequential execution with extra overhead, in this case. Again, in this case, what would hope to be achieved from doing things lazily, since the lazy operations would immediately be followed by their evaluation?
The parallel interface, which is async, is probably what you're lookin for.
The Python commands are encountered sequentially. One could image a library where the Python commands build the computation under the hood. Then, the library would be able to take advantage of situations like this one (or, more practically, reorder multiplications and/or avoid unnecessary temporaries).
We know what thinking machines does yet?
Job one is have every bit of software involved also be deterministic, which stagex takes care of.
I had no problem getting deterministic LLM outputs when I experimented with this 6 months ago.
Run two of these with the same prompts and same seed and you get the same results.
Obviously in GPU clusters with different hardware things get more complicated.
https://git.distrust.co/public/llmshell
That's not what this is about.
"I had no problem getting deterministic LLM outputs when I experimented with this 6 months ago" looks like you're using llama-cpp in that repo. This is about vllm serving many requests at once, at long sequence lengths.
> As it turns out, our request’s output does depend on the parallel user requests. Not because we’re somehow leaking information across batches — instead, it’s because our forward pass lacks “batch invariance”, causing our request’s output to depend on the batch size of our forward pass.
Your situation isn't really comparable.
What’s stagex?
supply chain security focused linux distro that does not trust its own maintainers by design.
It should also be noted that PyTorch has a page about reproducibility: https://docs.pytorch.org/docs/stable/notes/randomness.html
TL;DR
Seed your PRNGs and call torch.use_deterministic_algorithms(True) to get the deterministic kernels. They may be slightly slower, but in practice, you probably will not notice.
Note that results will still differ between different drivers and GPUs. It would be great if NVIDIA tried harder in that regard.
The blog post is about LLM non-determinism in the context of serving at scale (variable batch size). The page you link is only about run-to-run determinism implicitly assuming a fixed batch size.
His solution still relies on greedy (temperature 0) sampling, which is probably not optimal for model performance on various tasks. For example, Gemini 2.5 uses temperature 1 by default. But deterministic inference with temperature >0 can still be achieved by using pseudorandom sampling with a fixed seed.
Conceptually setting temperature to be >0 doesn't actually introduce any non-determinism. If your sampler is seeded then it will always choose the same next token. Higher temperature only flattens the logit distribution.
The point of the blog is that even at "supposed" deterministic generative sampling, non-determinism creeps in. This in turn has disastrous effects in very real experiments.
My point is that greedy sampling is not just not sufficient but also not necessary for deterministic inference.
cool project but if this is what you are producing with $2 billion funding, i doubt you will survive. This is the type of article a grad student would write over a weekend.
on the contrary this makes me bullish about their team, it shows that people here care about the craft
Who needs a working product when you can spend all day designing the most WEWORK looking website and slap some pseud slop on it. It's like crypto "startups" but it's not even fun.
I am baffled that I still run against these statement years after LLM's have been around. LLM's are deterministic and always have been. The reason people are having issues with them is because they are basing their assumptions on api based experiments. Like my man, how can you be making these statements when you haven't done the due diligence of running the LLM on your own hardware with all of the variables locked down and accounted for? If you do just that it would become obviously clear that they are deterministic and most of the time the reason you see the non deterministic behavior is because you have not controlled for a variable. Usually prompt caching, batch processing or some other obvious variable. Now this is related to within same system deterministic behavior. You might get different answers when running on a different gpu, but at least for same systems the behavior is 100% identical if you account for all server startup flags and properly account for things like prompt cashing, slot contamination etc...
I suggest you look up the name of the main author of TFA before assuming they don’t know what they are talking about.
This is literally one of the most knowledgeable person on the topic. I think you are the one that hasn’t peeled enough layers to connect with what they are saying.
Hold on a second. A transformer produces deterministically a probability distribution over the token alphabet from the context. Then one samples from this distribution. This is random and meant to be random.
The sampling process isn't random. If you sample with identical sampling parameters and identical values for said parameters, you will always get same results. You only start getting "non deterministic" behavior when you start using more complex systems outside the scope of your control like multi gpu systems and batch processing. One llm sampled with cash prompting off and and batch processing off will always generate same results if all values are same.
It's possible to deterministically sample from a probability distribution. For example, just seed your RNG with a constant, or with the SHA256 hash of the context.
Well yes, you can "hack" the pseudorandom number generator, but... that's not really the point when talking about determinism in LLMs is it? I mean the mathematical idea of the standard LLM is certainly truly random.
The article literally justifies This in the second paragraph.
I suppose I have issues with the way "determinism" is used in the title of this article. It can mean different things to different people and in my mind stating that "Defeating Nondeterminism in LLM Inference" frames it as an actual issue with LLM inference. But its not, its an issue with LLM inference when you start using large scale inference with more complex parts such as systems which use multi gpu inference systems or batching processes and other mechanisms. It is not an issue when using an LLM without those more complex parts. Stating it this way muddies the signal and gives a false sense that this is a fundamental issue with architecture, where its an issue of the systems at scale...