drbh c1cf36c0dc Improve qwen vl impl (#2943) ... * feat: refactor model, improve startup and re enable tests * fix: improve multimodal rotary embed caching * fix: limit vision flop calc to qwen2 vl models and update config typing * fix: include clippy lint * feat: refactor position ids in warmup and bump tests * fix: prefer default dtype * fix: enable all cuda graphs and bump snapshots * fix: adjust rotaty init path * fix: simplify get position ids and remove usused vision config * fix: update position ids so first dim is batch, simplify rotary and bump vlm default token limit * fix: improve position id init during cuda warmup for mrope and simplfy rotary forward * fix: check existance before accessing rope type in cuda warmup * fix: check key before access * fix: improve mrope check in cuda graph warmup * fix: remove check for default rope type * fix: add more test and improve model generation * fix: improve and simplify get_cos_sin, refactors and cleanup get_position_ids * fix: adjust signatures with types		2025-02-04 12:44:18 -05:00
..
custom_modeling	Improve qwen vl impl (#2943)	2025-02-04 12:44:18 -05:00
__init__.py	Improve qwen vl impl (#2943)	2025-02-04 12:44:18 -05:00
bloom.py	Refactor dead code - Removing all flash_xxx.py files. (#2166)	2024-07-05 10:29:56 +02:00
causal_lm.py	Sync (most) server dependencies with Nix (#2782)	2024-12-03 04:04:06 +01:00
flash_causal_lm.py	Improve qwen vl impl (#2943)	2025-02-04 12:44:18 -05:00
galactica.py	feat: add ruff and resolve issue (#2262)	2024-07-26 10:29:09 -04:00
globals.py	Fixing the oom maybe with 2.5.1 change. (#2958)	2025-01-28 10:30:28 +01:00
idefics_causal_lm.py	feat: prefill chunking (#2600)	2024-10-16 12:49:33 +02:00
mamba.py	Choosing input/total tokens automatically based on available VRAM? (#2673)	2024-10-28 04:59:49 +01:00
metadata_kernels.py	feat: add payload limit (#2726)	2024-11-21 18:20:15 +00:00
mllama_causal_lm.py	feat: add triton kernels to decrease latency of large batches (#2687)	2024-10-25 21:10:00 +00:00
model.py	Flash decoding kernel adding and prefill-chunking and prefix caching enabling in intel cpu/xpu (#2815)	2025-01-17 12:04:57 +01:00
pali_gemma.py	feat: add ruff and resolve issue (#2262)	2024-07-26 10:29:09 -04:00
seq2seq_lm.py	feat: prefill chunking (#2600)	2024-10-16 12:49:33 +02:00
transformers_flash_causal_lm.py	Transformers backend TP fix (#2945)	2025-01-23 18:09:57 +01:00
types.py	feat: prefill chunking (#2600)	2024-10-16 12:49:33 +02:00
vlm_causal_lm.py	Revert "feat: improve qwen2-vl startup " (#2924)	2025-01-17 12:09:05 -05:00