llama-bench : use random tokens to improve accuracy with mixtral #6069
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
ggerganov
approved these changes
Mar 15, 2024
There was a problem hiding this comment.
M2 Ultra
master
| model | size | params | backend | ngl | test | t/s |
|---|---|---|---|---|---|---|
| llama 7B F16 | 86.99 GiB | 46.70 B | Metal | 99 | pp 512 | 302.32 ± 0.54 |
| llama 7B F16 | 86.99 GiB | 46.70 B | Metal | 99 | pp 1024 | 301.49 ± 0.12 |
build: 4755afd (2431)
PR
| model | size | params | backend | ngl | test | t/s |
|---|---|---|---|---|---|---|
| llama 7B F16 | 86.99 GiB | 46.70 B | Metal | 99 | pp 512 | 275.43 ± 1.19 |
| llama 7B F16 | 86.99 GiB | 46.70 B | Metal | 99 | pp 1024 | 279.04 ± 0.67 |
build: 8281389 (2432)
hodlen
pushed a commit
to hodlen/llama.cpp
that referenced
this pull request
Apr 1, 2024
hodlen
pushed a commit
to hodlen/llama.cpp
that referenced
this pull request
Apr 3, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
llama-benchcurrently does not produce accurate results with mixtral because it uses the same token for the entire prompt (bos). This results in the same experts being chosen repeatedly, which is not what happens during real usage. With this changellama-benchuses random tokens instead.Current
llama-benchresults inmaster:Device 0: NVIDIA GeForce RTX 3090 Ti, compute capability 8.6, VMM: yes
build: 4755afd (2431)
Using
mainwith a large representative prompt (extracted from the frankenstein book text) produces these values instead:With
-ngl 0:With
-ngl 99:llama-benchafter this PR:Device 0: NVIDIA GeForce RTX 3090 Ti, compute capability 8.6, VMM: yes
The small difference is probably due to the warmup run performed by
llama-bench.Why is this important: a future change will cause all experts to be copied to VRAM during prompt processing regardless of if they are actually used, while currently only the experts used are copied. This change is important to understand the performance impact of doing that.