wangxiyuan 73acdcfc3b [PD] Correct the ip and port env (#2450) ...

1. rename `VLLM_LLMDD_RPC_PORT` to `VLLM_ASCEND_LLMDD_RPC_PORT` to make
the prefix the same in vllm-ascend
2. enable `VLLM_ASCEND_LLMDD_RPC_IP` env for PD feature.

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

2025-08-20 11:39:05 +08:00

..

attention

Fix some ci issue and refactor modelrunner (#2445)

2025-08-20 09:01:04 +08:00

compilation

Fix some ci issue and refactor modelrunner (#2445)

2025-08-20 09:01:04 +08:00

core

Disaggregate prefill for kv cache register style (#950)

2025-07-26 17:15:47 +08:00

device_allocator

[Misc]Clean up useless import from vllm (#2049)

2025-07-28 16:01:59 +08:00

distributed

[PD] Correct the ip and port env (#2450)

2025-08-20 11:39:05 +08:00

lora

Fix some ci issue and refactor modelrunner (#2445)

2025-08-20 09:01:04 +08:00

models

[improve] Remove redundant parentheses in pangu_moe.py (#2081)

2025-08-19 11:00:18 +08:00

multistream

[Quickfix] update CachedRequestState as NewRequestData changed (#2367)

2025-08-15 07:35:27 +08:00

ops

qwen3_moe/qwen25 support torchair graph (#2403)

2025-08-20 11:23:50 +08:00

patch

[Quickfix] update CachedRequestState as NewRequestData changed (#2367)

2025-08-15 07:35:27 +08:00

quantization

refactor select_experts of moe module (#2150)

2025-08-14 11:50:53 +08:00

sample

[Perf][MTP] Optimize reject sampler in greedy situation. (#2137)

2025-08-11 17:37:49 +08:00

torchair

qwen3_moe/qwen25 support torchair graph (#2403)

2025-08-20 11:23:50 +08:00

worker

Fix some ci issue and refactor modelrunner (#2445)

2025-08-20 09:01:04 +08:00

__init__.py

Bump torch version to 2.7.1 (#1562)

2025-08-05 08:43:24 +08:00

ascend_config.py

qwen3_moe/qwen25 support torchair graph (#2403)

2025-08-20 11:23:50 +08:00

ascend_forward_context.py

Fix some ci issue and refactor modelrunner (#2445)

2025-08-20 09:01:04 +08:00

envs.py

[PD] Correct the ip and port env (#2450)

2025-08-20 11:39:05 +08:00

meta_registration.py

Fix some ci issue and refactor modelrunner (#2445)

2025-08-20 09:01:04 +08:00

platform.py

Fix some ci issue and refactor modelrunner (#2445)

2025-08-20 09:01:04 +08:00

utils.py

[CustomOp] Register RMSNorm instead of overwrite forward_oot (#2284)

2025-08-14 17:18:30 +08:00