Nicolas Patry 5df8059037 Auto max prefill (#2797) ... * 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).		2024-12-06 05:52:00 +01:00
..
adapters	fix: avoid setting use_sgmv if no kernels present (#2796)	2024-12-04 15:26:09 -05:00
layers	Add support for wNa16 int 2:4 compressed-tensors checkpoints (#2758)	2024-11-20 18:25:23 +01:00
models	Auto max prefill (#2797)	2024-12-06 05:52:00 +01:00
pb	chore: add pre-commit (#1569)	2024-02-16 11:58:58 +01:00
utils	Move JSON grammar -> regex grammar conversion to the router (#2772)	2024-11-25 18:47:34 +01:00
__init__.py	feat(clients): Python client (#103)	2023-03-07 18:52:22 +01:00
cache.py	fix(server): decrease memory fragmentation (#557)	2023-07-06 14:28:33 +02:00
cli.py	Add initial support for compressed-tensors checkpoints (#2732)	2024-11-10 13:54:07 +01:00
interceptor.py	feat: prefill chunking (#2600)	2024-10-16 12:49:33 +02:00
server.py	Choosing input/total tokens automatically based on available VRAM? (#2673)	2024-10-28 04:59:49 +01:00
tracing.py	Add OTLP Service Name Environment Variable (#2076)	2024-06-25 09:33:01 +02:00