[foobar10000]

A question on the 100+ tps - is this for short prompts? For large contexts that generate a chunk of tokens at context sizes at 120k+, I was seeing 30-50 - and that's with 95% KV cache hit rate. Am wondering if I'm simply doing something wrong here...

[reissbaker]

Depends on how well the speculator predicts your prompts, assuming you're using speculative decoding — weird prompts are slower, but e.g. TypeScript code diffs should be very fast. For SGLang, you also want to use a larger chunked prefill size and larger max batch sizes for CUDA graphs than the defaults IME.