-
# pip3 install triton
Defaulting to user installation because normal site-packages is not writeable
ERROR: Could not find a version that satisfies the requirement triton (from versions: none)
ERROR…
-
Hi friends:
I installed triton from the source. But the triton compiler generates an error which is "AttributeError: module 'triton' has no attribute 'jit'". Someone knows how to solve this? Than…
-
Hi
I test bitblas models with the [https://github.com/ModelCloud/GPTQModel](https://github.com/ModelCloud/GPTQModel) repo.
I found that the output is correct. However, BitBLAS obtains similar to…
-
We created the following TTIR, which was previously working for us. However, it is now segfaulting at HEAD on main.
The TTIR is essentially loading 2 parameters (one s8, one f32), convert the s8 to…
-
[MLIR LSP server](https://mlir.llvm.org/docs/Tools/MLIRLSP/) is a tool for IDE to understand `.mlir` files of various dialects. By integrating with `mlir-lsp` related tools, we can make IDE aware of t…
-
**Is your feature request related to a problem? Please describe.**
A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
I am using TRTIS on jetson Orin versio…
-
either torch.compile / triton, forward / backward operations got too much activations that are probably bottlenecking training.
For some reason, i got about 30% speedup at 1B scale but does not seem …
-
### System Info
Tensorrt-LLM commit: 2a115dae84f13daaa54727534daa837c534eceb4
TensorRT-LLM version: 0.11.0.dev2024061800
### Who can help?
_No response_
### Information
- [X] The official exam…
-
### Feature Description
I would like to add support for Nvidia Triton TensorRT LLMs in llama index. There is currently support for several other LLM endpoints and Nvidia has several interesting offer…
-
~~Here's a theoretical example, but note that this doesn't actually repro (fx CSE doesn't seem to work in this case?). I'm seeing this with a much larger model and will try to get a real repro soon.~~…