-
> also noticed that the inverse + regular don't line up correctly such that they form a perfect arrow
That problem is already mentioned right in the top of this thread/PR, with a poss…
-
When export dynamic-shape llama2, in the attached [piece of the partitioned model](https://github.com/user-attachments/files/16568296/partitioned-model_piece-2.txt), there are symbol manipulations suc…
-
Consider the following example:
```
-- | The Martin-Löf equality type.
data Eq(implicit a: Type, x y: a) {
-- | The reflexivity constructor.
Refl(implicit a: Type, x: a): Eq(a:=a, x, x)…
-
### Version
1.7.0
### On which installation method(s) does this occur?
_No response_
### Describe the issue
When attempting to install the subprocess exits due to an error:
`TypeError: float() ar…
-
```
>> syms f(x)
>> syms y
>> limit(diff(f),y)
error: Python exception: NotImplementedError: Don't know how to calculate the mrv of 'Subs(Derivative(f(_p), _p), _p, y + 1/_p)'
occurred at lin…
-
I tried to quantize a 2B model, and when I run experiments/w4a8/main/e2e_llama-s1024-ep60-sym.sh, it used over 150GB vram...
Is this expected behaviour?
-
Here's the full log of build: https://github.com/abcfy2/aria2-static-build/actions/runs/11342690751/job/31543660613
The reason is:
```
cp ../../include/arch/mips/opensslconf.h opensslconf.h
ma…
-
Hi there. Do you plan to support `loongarch64` ? Since openssl already support this arch.
Toolchain: https://github.com/musl-cross/musl-cross/releases/download/20241103/loongarch64-unknown-linux-mu…
-
Dears,
I failed to run Llama-2-7b-chat-hf on NPU, please give me a hand.
1. I converted the mode by below command, and got two models,
a) optimum-cli export openvino --task text-generation -m Meta-…
-
To reproduce (polygon's point order doesn't matter):
```
namespace bg = boost::geometry;
namespace bgm = boost::geometry::model;
using cpt_t = bgm::point;
using cpo_t = bgm::polygon;
using cmp…