Qubitium-ModelCloud 56a724eba3 [QUANT] Add GPTQModel Dynamic Quantization + lm_head Quantization (#3790) ...

Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai>
Co-authored-by: ZX-ModelCloud <zx@modelcloud.ai>

2025-03-05 01:11:00 -08:00

..

configs

example: add vlm to token in & out example (#3941)

2025-03-04 22:18:26 -08:00

constrained

[Fix & Style] Refactor the grammar backend to reduce human errors and improve readability (#4030)

2025-03-04 03:56:45 -08:00

distributed

Clean up custom allreduce (#4029)

2025-03-03 04:59:53 -08:00

entrypoints

Reasoning parser (#4000)

2025-03-03 21:16:36 -08:00

layers

[QUANT] Add GPTQModel Dynamic Quantization + lm_head Quantization (#3790)

2025-03-05 01:11:00 -08:00

lora

[Fix] Fix bugs and refactor codes in lora for better scalability. (#3652)

2025-02-20 11:51:57 -08:00

managers

example: add vlm to token in & out example (#3941)

2025-03-04 22:18:26 -08:00

mem_cache

[Minor] more code cleanup (#4077)

2025-03-04 21:23:47 -08:00

metrics

Improve code styles (#4021)

2025-03-03 03:20:23 -08:00

model_executor

[Minor] more code cleanup (#4077)

2025-03-04 21:23:47 -08:00

model_loader

example: add vlm to token in & out example (#3941)

2025-03-04 22:18:26 -08:00

models

[QUANT] Add GPTQModel Dynamic Quantization + lm_head Quantization (#3790)

2025-03-05 01:11:00 -08:00

openai_api

Reasoning parser (#4000)

2025-03-03 21:16:36 -08:00

sampling

Remove outdated test utils and fix links for the doc of sampling params (#3999)

2025-03-03 09:41:38 -08:00

speculative

Simplify eagle tests and TP sync in grammar backend (#4066)

2025-03-04 13:40:40 -08:00

_custom_ops.py

Fix breakage problem when using custom_ar (#4052)

2025-03-04 02:59:03 -08:00

aio_rwlock.py

A better aio rwlock that guarantees the order (#2547)

2024-12-22 15:44:32 -08:00

conversation.py

[Feature] Support minicpmv v2.6 (#2785)

2025-01-18 14:14:19 -08:00

custom_op.py

Use forward_cuda to execute custom op for hip platform (#3305)

2025-02-05 02:58:17 +00:00

function_call_parser.py

[Minor] more code cleanup (#4077)

2025-03-04 21:23:47 -08:00

hf_transformers_utils.py

Model: Support Qwen 2.5 vl (#3258)

2025-02-16 00:58:53 -08:00

mm_utils.py

docs: fix module docstrings and copyright headers (#2077)

2024-11-22 22:16:53 +08:00

model_parallel.py

Make torch TP composable with torchao (#2436)

2024-12-11 04:21:42 -08:00

reasoning_parser.py

Reasoning parser (#4000)

2025-03-03 21:16:36 -08:00

server_args.py

Reasoning parser (#4000)

2025-03-03 21:16:36 -08:00

server.py

Misc fixes for eagle (flush_cache, CPU overhead) (#3014)

2025-01-20 20:27:38 -08:00

torch_memory_saver_adapter.py

Add a new api configure_logging to allow dumping the requests (#2875)

2025-01-13 14:24:00 -08:00

utils.py

[QUANT] Add GPTQModel Dynamic Quantization + lm_head Quantization (#3790)

2025-03-05 01:11:00 -08:00

warmup.py

Support penalty in overlap mode; return logprob with chunked prefill; improve benchmark scripts (#3988)

2025-03-03 00:12:04 -08:00