4 people f4b42df048 [Attention Backend] TurboQuant: 2-bit KV cache compression with 4x capacity (#38479) ...

Signed-off-by: vibhavagarwal5 <vibhavagarwal5@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Xinyu Chen <xinyu1.chen@intel.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>

2026-04-14 19:57:13 -07:00

..

__init__.py

[CI/Build] Move test_utils.py to tests/utils.py (#4425)

2024-05-13 23:50:09 +09:00

fp_quant.py

[Transform] [Quantization] Add QuTLASS support to vLLM (#24440)

2025-10-10 09:43:40 -07:00

reference_mxfp4.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

test_auto_round.py

Consolidate Intel Quantization Toolkit Integration in vLLM (#31716)

2026-01-14 07:11:30 +00:00

test_blackwell_moe.py

[MoE Refactor] Migrate Unquantized to Full Oracle Flow (#36286)

2026-03-31 15:43:33 -04:00

test_compressed_tensors.py

[Quant] add CompressedTensorsW8A8Mxfp8 for linear and MoE layers (#38815)

2026-04-11 17:21:36 -06:00

test_configs.py

[Hardware][AMD][CI][Bugfix] Fix AMD Quantization test group (#31713)

2026-01-10 23:19:46 -08:00

test_cpu_offload.py

[Hardware][AMD][CI][Bugfix] Fix AMD Quantization test group (#31713)

2026-01-10 23:19:46 -08:00

test_cpu_wna16.py

[CPU] Support CT W4A16 on CPU MP kernel (#38219)

2026-03-27 14:15:28 +08:00

test_experts_int8.py

[Quantization] Deprecate Long Tail of Schemes (#31688)

2026-01-08 19:07:45 -05:00

test_fp8.py

[W8A8 Block Linear Refactor][2/N] Remove W8A8Fp8BlockLinearOp and adopt Fp8 block linear kernel selections. (#33892)

2026-04-09 08:50:39 +08:00

test_gptq_dynamic.py

[Hardware][AMD][CI][Bugfix] Fix AMD Quantization test group (#31713)

2026-01-10 23:19:46 -08:00

test_gptq_v2.py

[Kernel] Add GPTQv2 format support for low-bit or asymmetric quantization, by adapting gptq_gemm (#26092)

2025-10-23 23:26:13 -04:00

test_lm_head.py

[CI Sprint] Quantization CI Cleanup (#24130)

2025-11-18 09:21:48 -05:00

test_mi3xx_moe.py

[ROCm][CI] Cleaning and restructuring amd-ci legacy pipeline (#34839)

2026-03-19 14:30:58 -05:00

test_mixed_precision.py

[CI] Bump mypy version to 1.19.1 (#36104)

2026-03-10 09:18:28 -07:00

test_modelopt.py

[W8A8 Block Linear Refactor][2/N] Remove W8A8Fp8BlockLinearOp and adopt Fp8 block linear kernel selections. (#33892)

2026-04-09 08:50:39 +08:00

test_online.py

[Frontend] new online quantization frontend (#38138)

2026-04-03 11:58:39 -04:00

test_per_token_kv_cache.py

[Feature] KV cache per-token-head INT8/FP8 quantization (#38378)

2026-04-02 08:13:26 -04:00

test_quark_maybe_update_config.py

[ROCm][Bugfix] fix exception related to trust_remote_code for MiniMax-M2.1-MXFP4 (#37698)

2026-03-30 15:49:23 +00:00

test_quark.py

[Quantization] Support Quark W8A8 INT8 MoE inference (#36320)

2026-04-09 17:24:43 +00:00

test_register_quantization_config.py

[CI Sprint] Quantization CI Cleanup (#24130)

2025-11-18 09:21:48 -05:00

test_torchao.py

Fix deprecated v1 config tests (#35327)

2026-03-01 20:32:03 -05:00

test_trtllm_nvfp4_hidden_dim_padding.py

[Kernel] Support TRTLLM GEN NVFP4 MoE for non-512-aligned hidden dims via weight padding (#39510)

2026-04-14 11:49:56 -07:00

test_turboquant.py

[Attention Backend] TurboQuant: 2-bit KV cache compression with 4x capacity (#38479)

2026-04-14 19:57:13 -07:00

utils.py

[Frontend] new online quantization frontend (#38138)

2026-04-03 11:58:39 -04:00