陈序
Any new info on this?
It seems that there are similar problems in: 1. ``dev::p2p::Host::saveNetwork() const`` 2. ``dev::p2p::PingNode::streamRLP(dev::RLPStream&) const`` 3. ``dev::p2p::Pong::streamRLP(dev::RLPStream&) const`` 4. ``void dev::rlpListAux`` 5. ``dev::eth::TransactionBase::streamRLP(dev::RLPStream&, dev::eth::IncludeSignature, bool) const``
> Nice catch, won't it be simpler to solve this by converting the deque to a list when iterating over it? I believe the code could stay the same as...
Hi @InkdyeHuang, thanks for your contribution. Did you get the same or similar results when using prompt prefix caching? Our team tried your code with llama but obtained incorrect results....
> Hi @HaiShaw > > Triton doesn't seem to support mixed precision dot product, so this kernel here fails if the `k` is uint8 and `q` is another precision. I've...
We tried to run 1.3b-base on TensorRT LLM with fp16 enabled, but got incorrect completion output.
1. Install [TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM/blob/main/README.md#installation) or [build it from source](https://github.com/NVIDIA/TensorRT-LLM/blob/main/docs/source/build_from_source.md). 2. Clone the TensorRT-LLM project and goto `examples/llama`. 3. Follow the instructions in [`examples/llama/README.md`](https://github.com/NVIDIA/TensorRT-LLM/blob/main/examples/llama/README.md). 4. Replace the model name in commands with...
> Hi @chenxu2048 Have u resolved the problem of deepseek? No, we chose vLLM finally. Same error occurred in TensorRT 8.6, TensorRT 9.0 and TensorRT-LLM, but we have no way...
> > > Hi @chenxu2048 Have u resolved the problem of deepseek? > > > > > > No, we chose vLLM finally. Same error occurred in TensorRT 8.6, TensorRT...
> > > > > Hi @chenxu2048 Have u resolved the problem of deepseek? > > > > > > > > > > > > No, we chose vLLM...