mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-19 13:52:07 +00:00
5df8059037
* Attempt at automatic max batch prefill. * Taking into account number of shards. * Adding more cards. * Adding A100 + H100 * Adding a few more cards. * Logprobs cost too much. * h100 better name, and keep factor of 2 * Damn inflated sparse tflops. * Typo in h100. * Updated the flops calculation (checked with fvcore). * chunking by default. * Fix prefix caching for chat completion since we removed logprobs. * More tests. * Dropping all the prefill logprobs. * Add a flag that enables users to get logprobs back. * Repairing prompt token counting. * Fixing a few tests. * Remove some scaffolding. * Attempting to reduces the issues (workarounds for now). |
||
|---|---|---|
| .. | ||
| benchmarks.py | ||
| common.js | ||
| filter.py | ||
| long_prompt2.py | ||
| long.js | ||
| long.py | ||
| Makefile | ||
| orca.py | ||
| poetry.lock | ||
| pyproject.toml | ||