4 people 43ed4143c4 [Quantization] Fp8 Channelwise Dynamic Per Token GroupedGEMM (#15587) ...

Signed-off-by: ElizaWszola <eliza@neuralmagic.com>
Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
Co-authored-by: ElizaWszola <eliza@neuralmagic.com>
Co-authored-by: Lucas Wilkinson <wilkinson.lucas@gmail.com>
Co-authored-by: ElizaWszola <ewszola@redhat.com>

2025-03-27 06:47:25 +00:00

..

compressed_tensors

[Quantization] Fp8 Channelwise Dynamic Per Token GroupedGEMM (#15587)

2025-03-27 06:47:25 +00:00

kernels

Revert "Fix non-contiguous input passed to Marlin kernel (#15319)" (#15398)

2025-03-24 20:43:51 -07:00

quark

dynamic distpatch of fp8 kernels (#14245)

2025-03-11 10:54:56 -04:00

utils

[Kernel] CUTLASS grouped gemm fp8 MoE kernel (#13972)

2025-03-27 00:54:44 +00:00

__init__.py

[Kernel] Add ModelOpt FP4 Checkpoint Support (#12520)

2025-03-12 05:13:11 +00:00

aqlm.py

[Quant] Add SupportsQuant to phi3 and clip (#13104)

2025-02-15 19:28:33 -08:00

awq_marlin.py

[Model] Support Grok1 (#13795)

2025-02-26 01:07:12 +00:00

awq_triton.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

awq.py

[Quant] Add SupportsQuant to phi3 and clip (#13104)

2025-02-15 19:28:33 -08:00

base_config.py

[Quant] Add SupportsQuant to phi3 and clip (#13104)

2025-02-15 19:28:33 -08:00

bitsandbytes.py

[Misc] Upgrade BNB version (#15183)

2025-03-24 05:51:42 +00:00

deepspeedfp.py

[Quant] Add SupportsQuant to phi3 and clip (#13104)

2025-02-15 19:28:33 -08:00

experts_int8.py

[Model] Support Grok1 (#13795)

2025-02-26 01:07:12 +00:00

fbgemm_fp8.py

dynamic distpatch of fp8 kernels (#14245)

2025-03-11 10:54:56 -04:00

fp8.py

[TPU] Avoid Triton Import (#15589)

2025-03-27 06:43:02 +00:00

gguf.py

[Bugfix] Fix broken CPU quantization due to triton import (#15038)

2025-03-18 08:57:39 -07:00

gptq_marlin_24.py

[Quant] Add SupportsQuant to phi3 and clip (#13104)

2025-02-15 19:28:33 -08:00

gptq_marlin.py

[Bugfix] Fix gptq_marlin for deepseek-v3 (#13750)

2025-03-05 12:25:53 +08:00

gptq.py

[Misc] set single whitespace between log sentences (#13771)

2025-02-25 10:26:12 +08:00

hqq_marlin.py

[Quant] Add SupportsQuant to phi3 and clip (#13104)

2025-02-15 19:28:33 -08:00

ipex_quant.py

[Quant] Add SupportsQuant to phi3 and clip (#13104)

2025-02-15 19:28:33 -08:00

kv_cache.py

[Attention] Flash Attention 3 - fp8 (#14570)

2025-03-20 01:14:20 -04:00

marlin.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

modelopt.py

[Kernel] Add ModelOpt FP4 Checkpoint Support (#12520)

2025-03-12 05:13:11 +00:00

moe_wna16.py

[Bugfix] Fix MoeWNA16Method activation (#14024)

2025-02-28 15:22:42 +00:00

neuron_quant.py

[Misc] set single whitespace between log sentences (#13771)

2025-02-25 10:26:12 +08:00

ptpc_fp8.py

[FP8] Refactor apply_fp8_linear and apply_fp8_linear_generic into an object (#14390)

2025-03-07 05:20:16 +00:00

qqq.py

[Quant] Add SupportsQuant to phi3 and clip (#13104)

2025-02-15 19:28:33 -08:00

schema.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

tpu_int8.py

[Quant] Add SupportsQuant to phi3 and clip (#13104)

2025-02-15 19:28:33 -08:00