Justin Waugh

starcoder -- not enough space in the context's memory pool

11

I'm getting errors with starcoder models when I try to include any non-trivial amount of tokens. I'm getting this with both my raw model (direct .bin) and quantized model regardless...

Via the `CTransformers` library we're using `ggml` library For increasing context length, which is necessary for local-mode CPU verison of `StarCoder`, sketch fails and can crash dropping the full kernel....

Seeking on Async FS is bugged / not-working

7

Here's a minimal example: ```python import fsspec import asyncio async def async_version(): print("Async Version") fs = fsspec.filesystem("http", asynchronous=True) session = await fs.set_session() file = await fs.open_async("https://example.com/") print("Starting Tell", file.tell(), "seeking...

Small change that allows directly using the recently released DeepSeek R1 Distils. Tested on TPU v4-8 for "deepseek-ai/DeepSeek-R1-Distill-Llama-8B" and it worked.

## Environment - Platform (select one): - [x] Anthropic API - [ ] AWS Bedrock - [ ] Google Vertex AI - [ ] Other: - Claude CLI version: 1.0.6...

## Environment - Platform (select one): - [x] Anthropic API - Claude CLI version: (lost my state, so i can't check -- was one version before v1.0.9) - Operating System:...

[Bug] Kimi K2 Thinking decode produces invalid tokens when using kt-kernel / kt-amx weights with cpu experts

4

### Checklist - [x] 1. I have searched related issues but cannot get the expected help. - [x] 2. The bug has not been fixed in the latest version. -...