youkaichao 63e7176f26

[Core][Refactor] move parallel_utils into vllm/distributed (#3950) ...

[WIP][Core][Refactor] move vllm/model_executor/parallel_utils into vllm/distributed and vllm/device_communicators (#3950)

2024-04-10 15:33:30 -07:00

..

async_engine

[CI] Try introducing isort. (#3495)

2024-03-25 07:59:47 -07:00

basic_correctness

[Test] Make model tests run again and remove --forked from pytest (#3631)

2024-03-28 21:06:40 -07:00

core

[Misc] [Core] Implement RFC "Augment BaseExecutor interfaces to enable hardware-agnostic speculative decoding" (#3837)

2024-04-09 11:44:15 -07:00

distributed

[Core][Refactor] move parallel_utils into vllm/distributed (#3950)

2024-04-10 15:33:30 -07:00

engine

[Core] [Frontend] Make detokenization optional (#3749)

2024-04-03 21:52:18 -07:00

entrypoints

[Core] enable out-of-tree model register (#3871)

2024-04-06 17:11:41 -07:00

fp8_kv

Enable scaled FP8 (e4m3fn) KV cache on ROCm (AMD GPU) (#3290)

2024-04-03 14:15:55 -07:00

kernels

Enable scaled FP8 (e4m3fn) KV cache on ROCm (AMD GPU) (#3290)

2024-04-03 14:15:55 -07:00

lora

[Core][Refactor] move parallel_utils into vllm/distributed (#3950)

2024-04-10 15:33:30 -07:00

metrics

Re-enable the 80 char line width limit (#3305)

2024-03-10 19:49:14 -07:00

model_executor

[Core] Enable hf_transfer by default if available (#3817)

2024-04-04 04:02:43 +00:00

models

[Core] enable out-of-tree model register (#3871)

2024-04-06 17:11:41 -07:00

prefix_caching

[Core][Bugfix]Refactor block manager for better testability (#3492)

2024-03-27 23:59:28 -07:00

prompts

[BugFix] Fix input positions for long context with sliding window (#2088)

2023-12-13 12:28:13 -08:00

quantization

[Misc] Add support for new autogptq checkpoint_format (#3689)

2024-04-01 19:32:01 -04:00

samplers

[Bugfix] handle prompt_logprobs in _apply_min_tokens_penalty (#3876)

2024-04-10 01:39:56 -07:00

spec_decode

[Misc] [Core] Implement RFC "Augment BaseExecutor interfaces to enable hardware-agnostic speculative decoding" (#3837)

2024-04-09 11:44:15 -07:00

tokenization

[Misc] Some minor simplifications to detokenization logic (#3670)

2024-04-01 13:22:06 -07:00

worker

[Misc] [Core] Implement RFC "Augment BaseExecutor interfaces to enable hardware-agnostic speculative decoding" (#3837)

2024-04-09 11:44:15 -07:00

__init__.py

[Small] Formatter only checks lints in changed files (#1528)

2023-10-31 15:39:38 -07:00

conftest.py

[Core][Refactor] move parallel_utils into vllm/distributed (#3950)

2024-04-10 15:33:30 -07:00

test_cache_block_hashing.py

[CI] Try introducing isort. (#3495)

2024-03-25 07:59:47 -07:00

test_config.py

Fix assertion failure in Qwen 1.5 with prefix caching enabled (#3373)

2024-03-14 13:56:57 -07:00

test_logits_processor.py

Migrate logits computation and gather to model_runner (#3233)

2024-03-20 23:25:01 +00:00

test_regression.py

[BugFix] Fix GC bug for LLM class (#2882)

2024-02-14 22:17:44 -08:00

test_sampling_params.py

[Bugfix] fix crash if max_tokens=None (#2570)

2024-01-23 22:38:55 -08:00

test_sequence.py

[Chunked Prefill][4/n] Chunked prefill scheduler. (#3853)

2024-04-05 10:17:58 -07:00