Thomas Parnell 54600709b6

[Model] Changes to MLPSpeculator to support tie_weights and input_scale (#5965) ...

Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Joshua Rosenkranz <jmrosenk@us.ibm.com>

2024-07-01 16:40:02 -07:00

..

__init__.py

Unmark more files as executable (#5962)

2024-06-28 17:34:56 -04:00

arctic.py

[mypy] Enable type checking for test directory (#5017)

2024-06-15 04:45:31 +00:00

baichuan.py

[Model][Bugfix] Implicit model flags and reenable Phi-3-Vision (#5896)

2024-06-27 09:08:10 -07:00

bloom.py

[Misc] Load FP8 kv-cache scaling factors from checkpoints (#4893)

2024-05-22 13:28:20 -07:00

chatglm.py

[Model][Bugfix] Implicit model flags and reenable Phi-3-Vision (#5896)

2024-06-27 09:08:10 -07:00

clip.py

[Core] Registry for processing model inputs (#5214)

2024-06-28 12:09:56 +00:00

commandr.py

[Model] LoRA support added for command-r (#5178)

2024-06-18 11:01:21 -07:00

dbrx.py

fix DbrxFusedNormAttention missing cache_config (#5340)

2024-06-07 14:10:21 -07:00

decilm.py

[Model] Add base class for LoRA-supported models (#5018)

2024-06-27 16:03:04 +08:00

deepseek_v2.py

Support Deepseek-V2 (#4650)

2024-06-28 13:24:57 -07:00

deepseek.py

[Misc] Load FP8 kv-cache scaling factors from checkpoints (#4893)

2024-05-22 13:28:20 -07:00

falcon.py

[Model] Add support for falcon-11B (#5069)

2024-05-27 16:41:43 -07:00

gemma2.py

[Model] Add Gemma 2 (#5908)

2024-06-27 13:33:56 -07:00

gemma.py

[Bugfix] Fix precisions in Gemma 1 (#5913)

2024-06-29 03:10:21 +00:00

gpt2.py

[Misc] Load FP8 kv-cache scaling factors from checkpoints (#4893)

2024-05-22 13:28:20 -07:00

gpt_bigcode.py

[Model][Bugfix] Implicit model flags and reenable Phi-3-Vision (#5896)

2024-06-27 09:08:10 -07:00

gpt_j.py

[Misc] Load FP8 kv-cache scaling factors from checkpoints (#4893)

2024-05-22 13:28:20 -07:00

gpt_neox.py

[Misc] Load FP8 kv-cache scaling factors from checkpoints (#4893)

2024-05-22 13:28:20 -07:00

interfaces.py

[Model][Bugfix] Implicit model flags and reenable Phi-3-Vision (#5896)

2024-06-27 09:08:10 -07:00

internlm2.py

[Misc] Load FP8 kv-cache scaling factors from checkpoints (#4893)

2024-05-22 13:28:20 -07:00

jais.py

[Misc] Load FP8 kv-cache scaling factors from checkpoints (#4893)

2024-05-22 13:28:20 -07:00

llama_embedding.py

[Model][Misc] Add e5-mistral-7b-instruct and Embedding API (#3734)

2024-05-11 11:30:37 -07:00

llama.py

[Model][Bugfix] Implicit model flags and reenable Phi-3-Vision (#5896)

2024-06-27 09:08:10 -07:00

llava_next.py

[CI/Build] Add TP test for vision models (#5892)

2024-06-29 15:45:54 +00:00

llava.py

[CI/Build] Add TP test for vision models (#5892)

2024-06-29 15:45:54 +00:00

minicpm.py

[Model][Bugfix] Implicit model flags and reenable Phi-3-Vision (#5896)

2024-06-27 09:08:10 -07:00

mixtral_quant.py

[Bugfix / Core] Prefix Caching Guards (merged with main) (#4846)

2024-05-27 15:18:17 -07:00

mixtral.py

[Model][Bugfix] Implicit model flags and reenable Phi-3-Vision (#5896)

2024-06-27 09:08:10 -07:00

mlp_speculator.py

[Model] Changes to MLPSpeculator to support tie_weights and input_scale (#5965)

2024-07-01 16:40:02 -07:00

mpt.py

[Misc] Load FP8 kv-cache scaling factors from checkpoints (#4893)

2024-05-22 13:28:20 -07:00

olmo.py

[Misc] Load FP8 kv-cache scaling factors from checkpoints (#4893)

2024-05-22 13:28:20 -07:00

opt.py

[Misc] Load FP8 kv-cache scaling factors from checkpoints (#4893)

2024-05-22 13:28:20 -07:00

orion.py

[Misc] Load FP8 kv-cache scaling factors from checkpoints (#4893)

2024-05-22 13:28:20 -07:00

phi3_small.py

[Kernel][Backend][Model] Blocksparse flash attention kernel and Phi-3-Small model (#4799)

2024-05-24 22:00:52 -07:00

phi3v.py

[CI/Build] Add TP test for vision models (#5892)

2024-06-29 15:45:54 +00:00

phi.py

[Model][Bugfix] Implicit model flags and reenable Phi-3-Vision (#5896)

2024-06-27 09:08:10 -07:00

qwen2_moe.py

[Misc] Load FP8 kv-cache scaling factors from checkpoints (#4893)

2024-05-22 13:28:20 -07:00

qwen2.py

[Model][Bugfix] Implicit model flags and reenable Phi-3-Vision (#5896)

2024-06-27 09:08:10 -07:00

qwen.py

[Model] Support Qwen-VL and Qwen-VL-Chat models with text-only inputs (#5710)

2024-06-22 02:07:08 +00:00

stablelm.py

[Misc] Load FP8 kv-cache scaling factors from checkpoints (#4893)

2024-05-22 13:28:20 -07:00

starcoder2.py

[Bugfix / Core] Prefix Caching Guards (merged with main) (#4846)

2024-05-27 15:18:17 -07:00

xverse.py

[Model][Bugfix] Implicit model flags and reenable Phi-3-Vision (#5896)

2024-06-27 09:08:10 -07:00