-
Notifications
You must be signed in to change notification settings - Fork 101
All issues
Issue creation is restricted in this repository
Issues
is:issue state:open
is:issue state:open
Search results
- Status: Open.#930 In pegainfer-project/pegainfer;
- Status: Open.#906 In pegainfer-project/pegainfer;
- Status: Open.#896 In pegainfer-project/pegainfer;
- Status: Open.#828 In pegainfer-project/pegainfer;
- Status: Open.#824 In pegainfer-project/pegainfer;
glm52: two NCCL copies in one process corrupt the TP4 prefill comm (missing libnccl.so symlink in shared lib dir)
staleAutomatically marked after inactivityAutomatically marked after inactivityStatus: Open.#810 In pegainfer-project/pegainfer;gemma4: define the KV cache contract for the two attention groups
staleAutomatically marked after inactivityAutomatically marked after inactivityStatus: Open.#807 In pegainfer-project/pegainfer;glm52: session-affinity / cache-aware decode routing for wide EP fleets
staleAutomatically marked after inactivityAutomatically marked after inactivityStatus: Open.#806 In pegainfer-project/pegainfer;GLM5.2 free-running EP: coordinate shutdown across rank engines
staleAutomatically marked after inactivityAutomatically marked after inactivityStatus: Open.#796 In pegainfer-project/pegainfer;GLM5.2: enable prefix caching with speculative decoding (persist drafter state)
enhancementNew feature or requestNew feature or requeststaleAutomatically marked after inactivityAutomatically marked after inactivityStatus: Open.#792 In pegainfer-project/pegainfer;[tracing] Migrate router→engine trace join from X-Request-Id stash to upstream vllm-server trace_headers
staleAutomatically marked after inactivityAutomatically marked after inactivityStatus: Open.#790 In pegainfer-project/pegainfer;GLM5.2 P/D: apply backpressure when RDMA fetch staging memory is temporarily exhausted
staleAutomatically marked after inactivityAutomatically marked after inactivityStatus: Open.#782 In pegainfer-project/pegainfer;