Skip to content

Ww20 pr cpu context pickle#252

Closed
hlin99 wants to merge 27 commits into
devfrom
ww20_PR_cpu_context_pickle
Closed

Ww20 pr cpu context pickle#252
hlin99 wants to merge 27 commits into
devfrom
ww20_PR_cpu_context_pickle

Conversation

@hlin99
Copy link
Copy Markdown
Owner

@hlin99 hlin99 commented May 13, 2026

What this PR does / why we need it:

Special notes for your reviewers:

If applicable:

  • this PR contains user facing changes - docs added
  • this PR contains unit tests

hlin99 added 7 commits May 12, 2026 07:47
Signed-off-by: Tony Lin <tony.lin@intel.com>
Signed-off-by: Tony Lin <tony.lin@intel.com>
Signed-off-by: Tony Lin <tony.lin@intel.com>
Signed-off-by: Tony Lin <tony.lin@intel.com>
Signed-off-by: Tony Lin <tony.lin@intel.com>
Signed-off-by: Tony Lin <tony.lin@intel.com>
Replace scattered if/else CPU/CUDA branches in vllm_multi_process_adapter
with a TransferContext abstraction (ABC + CudaTransferContext + CPUTransferContext).

- Add transfer_context.py with unified register/store/retrieve/poll interface
- Device-type dispatch centralized in create_transfer_context() factory
- Adapter delegates all transport logic via polymorphism, no branching
- Future transports (e.g. SHM) only need a new subclass, zero adapter changes

Signed-off-by: Tony Lin <tony.lin@intel.com>
hlin99 added 6 commits May 13, 2026 06:44
Signed-off-by: Tony Lin <tony.lin@intel.com>
Signed-off-by: Tony Lin <tony.lin@intel.com>
Signed-off-by: Tony Lin <tony.lin@intel.com>
Signed-off-by: Tony Lin <tony.lin@intel.com>
…t.register() to restore DeepSeek V4 compress_ratio

Signed-off-by: Tony Lin <tony.lin@intel.com>
…text

Signed-off-by: Tony Lin <tony.lin@intel.com>
hlin99 added 13 commits May 15, 2026 06:26
Signed-off-by: Tony Lin <tony.lin@intel.com>
Signed-off-by: Tony Lin <tony.lin@intel.com>
Signed-off-by: Tony Lin <tony.lin@intel.com>
Signed-off-by: Tony Lin <tony.lin@intel.com>
…in transfer-context registration

Signed-off-by: Tony Lin <tony.lin@intel.com>
…text for shm solution

Signed-off-by: Tony Lin <tony.lin@intel.com>
Signed-off-by: Tony Lin <tony.lin@intel.com>
Signed-off-by: Tony Lin <tony.lin@intel.com>
Signed-off-by: Tony Lin <tony.lin@intel.com>
Signed-off-by: Tony Lin <tony.lin@intel.com>
Signed-off-by: Tony Lin <tony.lin@intel.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant