7 Commits

Author	SHA1	Message	Date
Laurent Mazare	a52b76ae82	Expose the cudnn algo in the conv ops. (#2892) ... * Set the algo. * Expose the cudnn preferred algo for conv ops.	2025-04-14 08:25:32 +02:00
drbh	13c67226e6	feat: support microphone whisper streaming (#1678) ... * feat: support microphone whisper streaming * fix: cleanup print stmts and adjust how input is read * fix: remove incorrect comment * feat: split into new example and simplify * fix: feature flag example file * fix: fmt fixes * feat: simplify and remove redundant files	2024-02-12 18:01:21 +01:00
drbh	9cadd4e644	feat: support multithread spectrogram and small perf tweaks (#1674) ... * feat: support multithread spectrogram and small perf tweaks * feat: clippy improvement for loop variable * fix: add back speed up scale down logic * fix: readd mirroring logic * feat: prefer scoped thread and simplify/improve logic/traits	2024-02-08 21:54:12 +01:00
Laurent Mazare	85bea43e5b	Make the whisper model cloneable (#1200) ... * Add a quantized variant of llama2.c * Clippy fixes. * Make the whisper model cloneable.	2023-10-27 16:59:19 +01:00
Laurent Mazare	392fe02fba	Move the common quantized-nn code to a shared module. (#1063)	2023-10-09 06:22:22 +01:00
Laurent Mazare	aa53368aeb	Better control on the optional dequantization in QMatMul (#1049) ... * Cosmetic change to the quantized whisper model. * Fix the dequantization. * Add the dequantize all variable.	2023-10-07 10:16:18 +01:00
Laurent Mazare	e04c789230	Add a quantized variant of whisper (#1017) ... * Add the quantized-whisper model. * Quantized the whisper model. * Adapt the whisper example to handle quantization. * Add the quantized flag. * Load the proper weights.	2023-10-02 14:59:53 +01:00