Q3_K is now running at ~18.5 ms / token on CUDA,
so the gap to Q4_0 is only 10%.
It seems memory acccess pattern is more important for
performance than the amount of computation the kernel
does.
Stranegly enough, for the few prompts I tried with the 7B model
the responses looked perfectly reasonable. Only realized something
is not quite right when I tried the larger models and started getting
nonse back.
In any case, Q2_K single token evaluation time on an RTX 4080 in a Ryzen7950X
box iusing CUDA and model fully loaded on the GPU are
~15.5 ms for 7B, ~25.4 ms for 13B, and ~55.8 ms for 30B.
The max number of layers that fit in VRAM for The 65B is 32.
With that, we get ~330 ms per token, which is not that much faster
than just running on the CPU (~470 ms per token).
Performance is ~20% lower compared to Q4_K on the CPU.
This is to be expected, considering that we are memory bound
on the CPU and the 5-bit model is ~22% larger than the 4-bit.
On the GPU, single token prediction is about the same as Q4_0
for both, single token and batch prediction.
Performance is ~40% lower compared to Q4_K on the CPU.
This is to be expected, considering that we are memory bound
on the CPU and the 6-bit model is ~44% larger than the 4-bit.
On the GPU, single token prediction is ~6% lower than Q4_0,
batch mode (perplexity) is even closer (but still slower).
Performance is the same or perhaps very slightly better than Q4_0 on the CPU.
On the GPU, single token prediction is ~10% better than Q4_0,
batch mode (perplexity is about the same).
CUDA is not ideal - ~50% slower than Q4_0 for
single token prediction, about the same in batch
mode (perplexity). CPU single token is ~55 ms
(on Ryzen 7950X).
I think it is better to have quantization separate from
ggml. For now just adding the k-quants there, but it would be
better to also factor out the existing ggml quantizations.
This adds support to llama.cpp to load the model.
Currently missing are changes that are required from convert.py to convert the model correctly. It needs some changes to start reading the JSON configuration for HF models instead of deriving the values by guessing.
Co-authored-by: FNsi <125447286+FNsi@users.noreply.github.com>
1. Add a `LLAMA_SUPPORTS_GPU_OFFLOAD` define to `llama.h` (defined when compiled with CLBlast or cuBLAS)
2. Update the argument handling in the common example code to only show the `-ngl`, `--n-gpu-layers` option when GPU offload is possible.
3. Add an entry for the `-ngl`, `--n-gpu-layers` option to the `main` and `server` examples documentation
4. Update `main` and `server` examples documentation to use the new style dash separator argument format
5. Update the `server` example to use dash separators for its arguments and adds `-ngl` to `--help` (only shown when compiled with appropriate support). It will still support `--memory_f32` and `--ctx_size` for compatibility.
6. Add a warning discouraging use of `--memory-f32` for the `main` and `server` examples `--help` text as well as documentation. Rationale: https://github.com/ggerganov/llama.cpp/discussions/1593#discussioncomment-6004356
Set `LLAMA_BUILD_SERVER` in workflow so the `server` example gets build. This currently only applies to Windows builds because it seems like only Windows binary artifacts are included in releases.
Add `server` example target to `Makefile` (still uses `LLAMA_BUILD_SERVER` define and does not build by default)
Fix issue where `vdot` binary wasn't removed when running `make clean`.
Fix compile warnings in `server` example.
Add `.hpp` files to trigger workflow (the server example has one).
Improvements to loading the session with `--prompt-cache` in the `main` example.
1. Fix an issue where the `--seed` parameter was ignored when loading a cached prompt.
2. When loading a cached prompt, you previously had to specify the saved prompt (or a prefix of it) again. This pull changes that behavior to default to the prompt that was cached if a prompt wasn't specified by the user.
