Skip to content

Pull requests: EricLBuehler/mistral.rs

New pull request New
61 Open 937 Closed
61 Open 937 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Add the conformer backbone (phi4mm audio)
#1448 opened Jun 7, 2025 by EricLBuehler Loading…
21
Refactor model examples codex
#1439 opened Jun 6, 2025 by EricLBuehler Loading…
9
Support GLM4 model
#1437 opened Jun 6, 2025 by guoqingbao • Draft
9
Improved prefix caching for paged attention codex
#1435 opened Jun 5, 2025 by EricLBuehler • Draft
2
Server core: consolidate and unify route handlers and API surface
#1423 opened Jun 4, 2025 by matthewhaynesonline • Draft
1 task
@matthewhaynesonline
5
PagedAttention kv-cache quantization (F8E4M3)
#1400 opened Jun 2, 2025 by EricLBuehler Loading…
10
Proper batching support for Dia TTS
#1392 opened May 31, 2025 by EricLBuehler • Draft
2
[Experimental] Convert afq cpu to ggml
#1381 opened May 27, 2025 by EricLBuehler • Draft
2
Experiments with mistralrs-codex
#1344 opened May 17, 2025 by EricLBuehler • Draft
2
Add blockwise fp8 gemm kernel codex
#1343 opened May 17, 2025 by EricLBuehler Loading…
8
Fix AFQ8 parsing for --isq codex
#1341 opened May 17, 2025 by EricLBuehler Loading…
2
Support MLA for DeepSeek models
#1287 opened Apr 19, 2025 by EricLBuehler • Draft
1
Add Qwen 2.5 Omni models Additions to model or architectures
#1281 opened Apr 15, 2025 by EricLBuehler Loading…
2 of 7 tasks
1
Proper documentation with Sphinx
#1261 opened Apr 3, 2025 by EricLBuehler Loading…
1
Add tensorwide FP8 cuda quant kernel
#1258 opened Apr 3, 2025 by EricLBuehler • Draft
1
Implement blockwise scales for cuBLASlt matmul
#1256 opened Apr 1, 2025 by EricLBuehler • Draft
1
Add optimized RmsNorm and RoPE
#1236 opened Mar 25, 2025 by EricLBuehler Loading…
1
FlashMLA support
#1159 opened Feb 25, 2025 by EricLBuehler Loading…
1
Add a MISTRALRS_NO_CUBLASLT env var
#1151 opened Feb 16, 2025 by EricLBuehler Loading…
1
I-quant support (IQ4_XS, etc)
#1120 opened Feb 3, 2025 by EricLBuehler Loading…
1
MiniCPM-O 2.6 audio support
#1089 opened Jan 23, 2025 by EricLBuehler Loading…
5
Add an easy cli
#1087 opened Jan 23, 2025 by EricLBuehler • Draft
1
Move supports_attn_softmax logic to build.rs
#1085 opened Jan 23, 2025 by EricLBuehler • Draft
5
paged-attn:cuda fallback bf16 for compute_cap < 8.0
#1040 opened Jan 8, 2025 by haricot • Draft
1
Refactor transformer implementations, unifying common components
#1030 opened Jan 6, 2025 by p-e-w • Draft
1
ProTip! Add no:assignee to see everything that’s not assigned.